andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-07-03 14:09:24 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Merge branch 'main' into main

Browse Source
This commit is contained in:
Brandon Hancock (bhancock_ai)
2025-01-14 13:10:11 -05:00
committed by GitHub
parent 1792be220d 8ceeec7d36
commit 818bd141c6
13 changed files with 2397 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
docs/concepts/flows.mdx
View File

@@ -35,6 +35,8 @@ class ExampleFlow(Flow):
@start()
def generate_city(self):
print("Starting flow")
# Each flow state automatically gets a unique ID
print(f"Flow State ID: {self.state['id']}")
response = completion(
model=self.model,
@@ -47,6 +49,8 @@ class ExampleFlow(Flow):
)
random_city = response["choices"][0]["message"]["content"]
# Store the city in our state
self.state["city"] = random_city
print(f"Random City: {random_city}")
return random_city
@@ -64,6 +68,8 @@ class ExampleFlow(Flow):
)
fun_fact = response["choices"][0]["message"]["content"]
# Store the fun fact in our state
self.state["fun_fact"] = fun_fact
return fun_fact
@@ -76,7 +82,15 @@ print(f"Generated fun fact: {result}")
In the above example, we have created a simple Flow that generates a random city using OpenAI and then generates a fun fact about that city. The Flow consists of two tasks: `generate_city` and `generate_fun_fact`. The `generate_city` task is the starting point of the Flow, and the `generate_fun_fact` task listens for the output of the `generate_city` task.
When you run the Flow, it will generate a random city and then generate a fun fact about that city. The output will be printed to the console.
Each Flow instance automatically receives a unique identifier (UUID) in its state, which helps track and manage flow executions. The state can also store additional data (like the generated city and fun fact) that persists throughout the flow's execution.
When you run the Flow, it will:
1. Generate a unique ID for the flow state
2. Generate a random city and store it in the state
3. Generate a fun fact about that city and store it in the state
4. Print the results to the console
The state's unique ID and stored data can be useful for tracking flow executions and maintaining context between tasks.
**Note:** Ensure you have set up your `.env` file to store your `OPENAI_API_KEY`. This key is necessary for authenticating requests to the OpenAI API.
@@ -207,14 +221,17 @@ allowing developers to choose the approach that best fits their application's ne
In unstructured state management, all state is stored in the `state` attribute of the `Flow` class.
This approach offers flexibility, enabling developers to add or modify state attributes on the fly without defining a strict schema.
Even with unstructured states, CrewAI Flows automatically generates and maintains a unique identifier (UUID) for each state instance.
```python Code
from crewai.flow.flow import Flow, listen, start
class UntructuredExampleFlow(Flow):
class UnstructuredExampleFlow(Flow):
@start()
def first_method(self):
# The state automatically includes an 'id' field
print(f"State ID: {self.state['id']}")
self.state.message = "Hello from structured flow"
self.state.counter = 0
@@ -231,10 +248,12 @@ class UntructuredExampleFlow(Flow):
print(f"State after third_method: {self.state}")
flow = UntructuredExampleFlow()
flow = UnstructuredExampleFlow()
flow.kickoff()
```
**Note:** The `id` field is automatically generated and preserved throughout the flow's execution. You don't need to manage or set it manually, and it will be maintained even when updating the state with new data.
**Key Points:**
- **Flexibility:** You can dynamically add attributes to `self.state` without predefined constraints.
@@ -245,12 +264,15 @@ flow.kickoff()
Structured state management leverages predefined schemas to ensure consistency and type safety across the workflow.
By using models like Pydantic's `BaseModel`, developers can define the exact shape of the state, enabling better validation and auto-completion in development environments.
Each state in CrewAI Flows automatically receives a unique identifier (UUID) to help track and manage state instances. This ID is automatically generated and managed by the Flow system.
```python Code
from crewai.flow.flow import Flow, listen, start
from pydantic import BaseModel
class ExampleState(BaseModel):
# Note: 'id' field is automatically added to all states
counter: int = 0
message: str = ""
@@ -259,6 +281,8 @@ class StructuredExampleFlow(Flow[ExampleState]):
@start()
def first_method(self):
# Access the auto-generated ID if needed
print(f"State ID: {self.state.id}")
self.state.message = "Hello from structured flow"
@listen(first_method)
@@ -628,4 +652,4 @@ Also, check out our YouTube video on how to use flows in CrewAI below!
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
referrerpolicy="strict-origin-when-cross-origin"
allowfullscreen
></iframe>
></iframe>

2
pyproject.toml
View File

@@ -11,7 +11,7 @@ dependencies = [
# Core Dependencies
"pydantic>=2.4.2",
"openai>=1.13.3",
"litellm>=1.44.22",
"litellm==1.57.4",
"instructor>=1.3.3",
# Text Processing

74
src/crewai/flow/flow.py
View File

@@ -13,9 +13,10 @@ from typing import (
Union,
cast,
)
from uuid import uuid4
from blinker import Signal
from pydantic import BaseModel, ValidationError
from pydantic import BaseModel, Field, ValidationError
from crewai.flow.flow_events import (
FlowFinishedEvent,
@@ -27,7 +28,12 @@ from crewai.flow.flow_visualizer import plot_flow
from crewai.flow.utils import get_possible_return_constants
from crewai.telemetry import Telemetry
T = TypeVar("T", bound=Union[BaseModel, Dict[str, Any]])
class FlowState(BaseModel):
"""Base model for all flow states, ensuring each state has a unique ID."""
id: str = Field(default_factory=lambda: str(uuid4()), description="Unique identifier for the flow state")
T = TypeVar("T", bound=Union[FlowState, Dict[str, Any]])
def start(condition: Optional[Union[str, dict, Callable]] = None) -> Callable:
@@ -377,14 +383,37 @@ class Flow(Generic[T], metaclass=FlowMeta):
self._methods[method_name] = getattr(self, method_name)
def _create_initial_state(self) -> T:
# Handle case where initial_state is None but we have a type parameter
if self.initial_state is None and hasattr(self, "_initial_state_T"):
return self._initial_state_T() # type: ignore
state_type = getattr(self, "_initial_state_T")
if isinstance(state_type, type):
if issubclass(state_type, FlowState):
return state_type() # type: ignore
elif issubclass(state_type, BaseModel):
# Create a new type that includes the ID field
class StateWithId(state_type, FlowState): # type: ignore
pass
return StateWithId() # type: ignore
# Handle case where no initial state is provided
if self.initial_state is None:
return {} # type: ignore
elif isinstance(self.initial_state, type):
return self.initial_state()
else:
return self.initial_state
return {"id": str(uuid4())} # type: ignore
# Handle case where initial_state is a type (class)
if isinstance(self.initial_state, type):
if issubclass(self.initial_state, FlowState):
return self.initial_state() # type: ignore
elif issubclass(self.initial_state, BaseModel):
# Create a new type that includes the ID field
class StateWithId(self.initial_state, FlowState): # type: ignore
pass
return StateWithId() # type: ignore
# Handle dictionary case
if isinstance(self.initial_state, dict) and "id" not in self.initial_state:
self.initial_state["id"] = str(uuid4())
return self.initial_state # type: ignore
@property
def state(self) -> T:
@@ -396,10 +425,17 @@ class Flow(Generic[T], metaclass=FlowMeta):
return self._method_outputs
def _initialize_state(self, inputs: Dict[str, Any]) -> None:
if isinstance(self._state, BaseModel):
if isinstance(self._state, dict):
# Preserve the ID when updating unstructured state
current_id = self._state.get("id")
self._state.update(inputs)
if current_id:
self._state["id"] = current_id
elif "id" not in self._state:
self._state["id"] = str(uuid4())
elif isinstance(self._state, BaseModel):
# Structured state
try:
def create_model_with_extra_forbid(
base_model: Type[BaseModel],
) -> Type[BaseModel]:
@@ -409,16 +445,28 @@ class Flow(Generic[T], metaclass=FlowMeta):
return ModelWithExtraForbid
# Get current state as dict, preserving the ID if it exists
state_model = cast(BaseModel, self._state)
current_state = (
state_model.model_dump()
if hasattr(state_model, "model_dump")
else state_model.dict()
if hasattr(state_model, "dict")
else {
k: v
for k, v in state_model.__dict__.items()
if not k.startswith("_")
}
)
ModelWithExtraForbid = create_model_with_extra_forbid(
self._state.__class__
)
self._state = cast(
T, ModelWithExtraForbid(**{**self._state.model_dump(), **inputs})
T, ModelWithExtraForbid(**{**current_state, **inputs})
)
except ValidationError as e:
raise ValueError(f"Invalid inputs for structured state: {e}") from e
elif isinstance(self._state, dict):
self._state.update(inputs)
else:
raise TypeError("State must be a BaseModel instance or a dictionary.")

4
src/crewai/utilities/llm_utils.py
View File

@@ -1,11 +1,7 @@
import os
from typing import Any, Dict, List, Optional, Union
from packaging import version
from crewai.cli.constants import DEFAULT_LLM_MODEL, ENV_VARS, LITELLM_PARAMS
from crewai.cli.utils import read_toml
from crewai.cli.version import get_crewai_version
from crewai.llm import LLM

2
tests/agent_test.py
View File

@@ -1495,7 +1495,7 @@ def test_agent_execute_task_basic():
role="test role",
goal="test goal",
backstory="test backstory",
llm=LLM(model="gpt-3.5-turbo"),
llm="gpt-4o-mini",
)
task = Task(

70
tests/cassettes/test_agent_execute_task_basic.yaml
View File

@@ -2,14 +2,15 @@ interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nTo give my best complete final answer to the task
use the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!"}, {"role": "user", "content": "\nCurrent Task: Calculate 2 + 2\n\nThis
is the expect criteria for your final answer: The result of the calculation\nyou
respond using the exact following format:\n\nThought: I now can give a great
answer\nFinal Answer: Your final answer must be the great and the most complete
as possible, it must be outcome described.\n\nI MUST use these formats, my job
depends on it!"}, {"role": "user", "content": "\nCurrent Task: Calculate 2 +
2\n\nThis is the expect criteria for your final answer: The result of the calculation\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-3.5-turbo"}'
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
["\nObservation:"]}'
headers:
accept:
- application/json
@@ -18,16 +19,13 @@ interactions:
connection:
- keep-alive
content-length:
- '797'
- '833'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
@@ -37,29 +35,35 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7WSAKkoU8Nfy5KZwYNlMSpoaSeY\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213888,\n \"model\": \"gpt-3.5-turbo-0125\",\n
content: "{\n \"id\": \"chatcmpl-AoJqi2nPubKHXLut6gkvISe0PizvR\",\n \"object\":
\"chat.completion\",\n \"created\": 1736556064,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer\\n\\nFinal
Answer: 2 + 2 = 4\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
159,\n \"completion_tokens\": 19,\n \"total_tokens\": 178,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: The result of the calculation 2 + 2 is 4.\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 161,\n \"completion_tokens\":
25,\n \"total_tokens\": 186,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85eb70a9401cf3-GRU
- 9000dbe81c55bf7f-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -67,37 +71,45 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:08 GMT
- Sat, 11 Jan 2025 00:41:05 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=LCNQO7gfz6xDjDqEOZ7ha3jDwPnDlsjsmJyScVf4UUw-1736556065-1.0.1.1-2ZcyBDpLvmxy7UOdCrLd6falFapRDuAu6WcVrlOXN0QIgZiDVYD0bCFWGCKeeE.6UjPHoPY6QdlEZZx8.0Pggw;
path=/; expires=Sat, 11-Jan-25 01:11:05 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=cRATWhxkeoeSGFg3z7_5BrHO3JDsmDX2Ior2i7bNF4M-1736556065175-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '489'
- '1060'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '50000000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '29999'
x-ratelimit-remaining-tokens:
- '49999813'
- '149999810'
x-ratelimit-reset-requests:
- 6ms
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_66c2e9625c005de2d6ffcec951018ec9
- req_463fbd324e01320dc253008f919713bd
http_version: HTTP/1.1
status_code: 200
version: 1

461
tests/cassettes/test_agent_execute_task_with_ollama.yaml
View File

@@ -2,44 +2,457 @@ interactions:
- request:
body: '{"model": "llama3.2:3b", "prompt": "### System:\nYou are test role. test
backstory\nYour personal goal is: test goal\nTo give my best complete final
answer to the task use the exact following format:\n\nThought: I now can give
a great answer\nFinal Answer: Your final answer must be the great and the most
complete as possible, it must be outcome described.\n\nI MUST use these formats,
my job depends on it!\n\n### User:\n\nCurrent Task: Explain what AI is in one
sentence\n\nThis is the expect criteria for your final answer: A one-sentence
answer to the task respond using the exact following format:\n\nThought: I now
can give a great answer\nFinal Answer: Your final answer must be the great and
the most complete as possible, it must be outcome described.\n\nI MUST use these
formats, my job depends on it!\n\n### User:\n\nCurrent Task: Explain what AI
is in one sentence\n\nThis is the expect criteria for your final answer: A one-sentence
explanation of AI\nyou MUST return the actual complete content as the final
answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:\n\n",
"options": {"stop": ["\nObservation:"]}, "stream": false}'
headers:
Accept:
accept:
- '*/*'
Accept-Encoding:
accept-encoding:
- gzip, deflate
Connection:
connection:
- keep-alive
Content-Length:
- '839'
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
content-length:
- '849'
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/generate
response:
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:05:52.24992Z","response":"Final
Answer: Artificial Intelligence (AI) refers to the development of computer
systems capable of performing tasks that typically require human intelligence,
such as learning, problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,13171,315,16785,9256,430,11383,1397,3823,11478,11,1778,439,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1461909875,"load_duration":39886208,"prompt_eval_count":181,"prompt_eval_duration":701000000,"eval_count":39,"eval_duration":719000000}'
content: '{"model":"llama3.2:3b","created_at":"2025-01-10T18:39:31.893206Z","response":"Final
Answer: Artificial Intelligence (AI) refers to the development of computer systems
that can perform tasks that typically require human intelligence, including
learning, problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,6013,1701,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,430,649,2804,9256,430,11383,1397,3823,11478,11,2737,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":2216514375,"load_duration":38144042,"prompt_eval_count":182,"prompt_eval_duration":1415000000,"eval_count":38,"eval_duration":759000000}'
headers:
Content-Length:
- '1537'
- '1534'
Content-Type:
- application/json; charset=utf-8
Date:
- Thu, 02 Jan 2025 20:05:52 GMT
status:
code: 200
message: OK
- Fri, 10 Jan 2025 18:39:31 GMT
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Fri, 10 Jan 2025 18:39:31 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
version: 1

869
tests/cassettes/test_agent_with_ollama_llama3.yaml
View File

@@ -1,36 +1,863 @@
interactions:
- request:
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who
which model are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream":
false}'
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Which
model are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream": false}'
headers:
Accept:
accept:
- '*/*'
Accept-Encoding:
accept-encoding:
- gzip, deflate
Connection:
connection:
- keep-alive
Content-Length:
- '156'
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
content-length:
- '152'
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/generate
response:
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:07:07.623404Z","response":"I''m
an AI designed to assist and communicate with users, utilizing a combination
of natural language processing models.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,902,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,7945,323,19570,449,3932,11,35988,264,10824,315,5933,4221,8863,4211,13],"total_duration":1076617833,"load_duration":46505416,"prompt_eval_count":40,"prompt_eval_duration":626000000,"eval_count":22,"eval_duration":399000000}'
content: '{"model":"llama3.2:3b","created_at":"2025-01-10T18:37:01.552946Z","response":"I''m
an AI designed by Meta, leveraging large language models to provide information
and assist with various tasks.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,555,16197,11,77582,3544,4221,4211,311,3493,2038,323,7945,449,5370,9256,13],"total_duration":2721386667,"load_duration":838784333,"prompt_eval_count":39,"prompt_eval_duration":1462000000,"eval_count":22,"eval_duration":418000000}'
headers:
Content-Length:
- '690'
- '683'
Content-Type:
- application/json; charset=utf-8
Date:
- Thu, 02 Jan 2025 20:07:07 GMT
status:
code: 200
message: OK
- Fri, 10 Jan 2025 18:37:01 GMT
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Fri, 10 Jan 2025 18:37:01 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Fri, 10 Jan 2025 18:37:01 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
version: 1

866
tests/cassettes/test_llm_call_with_ollama_llama3.yaml
View File

@@ -1,36 +1,864 @@
interactions:
- request:
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Which
model are you??\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream":
model are you?\n\n", "options": {"temperature": 0.7, "num_predict": 30}, "stream":
false}'
headers:
Accept:
accept:
- '*/*'
Accept-Encoding:
accept-encoding:
- gzip, deflate
Connection:
connection:
- keep-alive
Content-Length:
- '164'
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
content-length:
- '163'
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/generate
response:
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:24:24.812595Z","response":"I''m
an AI, specifically a large language model, designed to understand and respond
to user queries with accuracy.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,71291,128009,128006,78191,128007,271,40,2846,459,15592,11,11951,264,3544,4221,1646,11,6319,311,3619,323,6013,311,1217,20126,449,13708,13],"total_duration":827817584,"load_duration":41560542,"prompt_eval_count":39,"prompt_eval_duration":384000000,"eval_count":23,"eval_duration":400000000}'
content: '{"model":"llama3.2:3b","created_at":"2025-01-10T22:34:56.01157Z","response":"I''m
an artificial intelligence model, specifically a transformer-based language
model, designed to provide helpful and informative responses.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,21075,11478,1646,11,11951,264,43678,6108,4221,1646,11,6319,311,3493,11190,323,39319,14847,13],"total_duration":579515000,"load_duration":35352208,"prompt_eval_count":39,"prompt_eval_duration":126000000,"eval_count":23,"eval_duration":417000000}'
headers:
Content-Length:
- '683'
- '714'
Content-Type:
- application/json; charset=utf-8
Date:
- Thu, 02 Jan 2025 20:24:24 GMT
status:
code: 200
message: OK
- Fri, 10 Jan 2025 22:34:56 GMT
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Fri, 10 Jan 2025 22:34:56 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.57.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Fri, 10 Jan 2025 22:34:56 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
version: 1

74
tests/cassettes/test_llm_callback_replacement.yaml
View File

@@ -1,7 +1,6 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Hello, world!"}], "model": "gpt-4o-mini",
"stream": false}'
body: '{"messages": [{"role": "user", "content": "Hello, world!"}], "model": "gpt-4o-mini"}'
headers:
accept:
- application/json
@@ -10,13 +9,13 @@ interactions:
connection:
- keep-alive
content-length:
- '101'
- '84'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
@@ -26,7 +25,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
@@ -38,22 +37,22 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AcdBV2knOF2soWLszceiA08K8W8nE\",\n \"object\":
\"chat.completion\",\n \"created\": 1733770453,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
content: "{\n \"id\": \"chatcmpl-AoEzIjusutsoPh1EmGgeXifkYvbfH\",\n \"object\":
\"chat.completion\",\n \"created\": 1736537376,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Hello! How can I assist you today?\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 11,\n \"completion_tokens\":
9,\n \"total_tokens\": 20,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
10,\n \"total_tokens\": 21,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_bba3c8e70b\"\n}\n"
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_01aeff40ea\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ef733d51801bada-ATL
- 8fff13aa78db4569-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -61,14 +60,14 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 09 Dec 2024 18:54:13 GMT
- Fri, 10 Jan 2025 19:29:36 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=_fEt57lre0.E_IZaebjaDAcrpBbzGhLWW6KtQ4FjLxo-1733770453-1.0.1.1-ndzEQCfExSp1asSdBXxS0fGYQnKVTivInc1MHN.ZjnmGmkAmEp0EPwiJlcAMvQaMCMZ7a_vKqAEMbz8ZbzTYYg;
path=/; expires=Mon, 09-Dec-24 19:24:13 GMT; domain=.api.openai.com; HttpOnly;
- __cf_bm=PoW0e3SDy04AxLoIfTXlp2oFUuTGjQzesTybc7KXe28-1736537376-1.0.1.1-tznDR3VZpUOrVUyHmDUYYtpSQ2WI3X6ya9EhOwgNEMVIe6KsDgje4tO7z_tk7l0cuRww1jx_ryG3sgT1AETdVw;
path=/; expires=Fri, 10-Jan-25 19:59:36 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=2gTS3no9rova7t6URcfR30yzeZdKkL.9.lvsZXgmbVw-1733770453657-0.0.1.1-604800000;
- _cfuvid=3UeEmz_rnmsoZxrVUv32u35gJOi766GDWNe5_RTjiPk-1736537376739-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
@@ -81,7 +80,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '275'
- '286'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -99,12 +98,12 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_82ef8940a3291813e6a347535ab6bf26
- req_18f5593ddf37824bb9a7690407170dc0
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Hello, world from another agent!"}],
"model": "gpt-4o-mini", "stream": false}'
"model": "gpt-4o-mini"}'
headers:
accept:
- application/json
@@ -113,16 +112,16 @@ interactions:
connection:
- keep-alive
content-length:
- '120'
- '103'
content-type:
- application/json
cookie:
- __cf_bm=_fEt57lre0.E_IZaebjaDAcrpBbzGhLWW6KtQ4FjLxo-1733770453-1.0.1.1-ndzEQCfExSp1asSdBXxS0fGYQnKVTivInc1MHN.ZjnmGmkAmEp0EPwiJlcAMvQaMCMZ7a_vKqAEMbz8ZbzTYYg;
_cfuvid=2gTS3no9rova7t6URcfR30yzeZdKkL.9.lvsZXgmbVw-1733770453657-0.0.1.1-604800000
- __cf_bm=PoW0e3SDy04AxLoIfTXlp2oFUuTGjQzesTybc7KXe28-1736537376-1.0.1.1-tznDR3VZpUOrVUyHmDUYYtpSQ2WI3X6ya9EhOwgNEMVIe6KsDgje4tO7z_tk7l0cuRww1jx_ryG3sgT1AETdVw;
_cfuvid=3UeEmz_rnmsoZxrVUv32u35gJOi766GDWNe5_RTjiPk-1736537376739-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
@@ -132,7 +131,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
@@ -144,22 +143,23 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AcdBWMAembczwWDLdjIRYwtbMLONh\",\n \"object\":
\"chat.completion\",\n \"created\": 1733770454,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
content: "{\n \"id\": \"chatcmpl-AoEzIOYUDsd7SpYDQeQmbNGS7IBLE\",\n \"object\":
\"chat.completion\",\n \"created\": 1736537376,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Hello! It\u2019s great to connect with
you. How can I assist you today?\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
14,\n \"completion_tokens\": 17,\n \"total_tokens\": 31,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_bba3c8e70b\"\n}\n"
\"assistant\",\n \"content\": \"Hello! It's great to connect with another
agent. How can I assist you today?\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 14,\n \"completion_tokens\": 18,\n
\ \"total_tokens\": 32,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_01aeff40ea\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ef733d7bc41bada-ATL
- 8fff13ad8e054569-ATL
Connection:
- keep-alive
Content-Encoding:
@@ -167,7 +167,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 09 Dec 2024 18:54:14 GMT
- Fri, 10 Jan 2025 19:29:37 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -181,7 +181,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '659'
- '422'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -199,7 +199,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_da24049df911504f5102825db6b4aea9
- req_366bcd7dfe94e2a2b5640fd9bb1c5a6b
http_version: HTTP/1.1
status_code: 200
version: 1

76
tests/flow_test.py
View File

@@ -3,6 +3,7 @@
import asyncio
import pytest
from pydantic import BaseModel
from crewai.flow.flow import Flow, and_, listen, or_, router, start
@@ -265,6 +266,81 @@ def test_flow_with_custom_state():
assert flow.counter == 2
def test_flow_uuid_unstructured():
"""Test that unstructured (dictionary) flow states automatically get a UUID that persists."""
initial_id = None
class UUIDUnstructuredFlow(Flow):
@start()
def first_method(self):
nonlocal initial_id
# Verify ID is automatically generated
assert "id" in self.state
assert isinstance(self.state["id"], str)
# Store initial ID for comparison
initial_id = self.state["id"]
# Add some data to trigger state update
self.state["data"] = "example"
@listen(first_method)
def second_method(self):
# Ensure the ID persists after state updates
assert "id" in self.state
assert self.state["id"] == initial_id
# Update state again to verify ID preservation
self.state["more_data"] = "test"
assert self.state["id"] == initial_id
flow = UUIDUnstructuredFlow()
flow.kickoff()
# Verify ID persists after flow completion
assert flow.state["id"] == initial_id
# Verify UUID format (36 characters, including hyphens)
assert len(flow.state["id"]) == 36
def test_flow_uuid_structured():
"""Test that structured (Pydantic) flow states automatically get a UUID that persists."""
initial_id = None
class MyStructuredState(BaseModel):
counter: int = 0
message: str = "initial"
class UUIDStructuredFlow(Flow[MyStructuredState]):
@start()
def first_method(self):
nonlocal initial_id
# Verify ID is automatically generated and accessible as attribute
assert hasattr(self.state, "id")
assert isinstance(self.state.id, str)
# Store initial ID for comparison
initial_id = self.state.id
# Update some fields to trigger state changes
self.state.counter += 1
self.state.message = "updated"
@listen(first_method)
def second_method(self):
# Ensure the ID persists after state updates
assert hasattr(self.state, "id")
assert self.state.id == initial_id
# Update state again to verify ID preservation
self.state.counter += 1
self.state.message = "final"
assert self.state.id == initial_id
flow = UUIDStructuredFlow()
flow.kickoff()
# Verify ID persists after flow completion
assert flow.state.id == initial_id
# Verify UUID format (36 characters, including hyphens)
assert len(flow.state.id) == 36
# Verify other state fields were properly updated
assert flow.state.counter == 2
assert flow.state.message == "final"
def test_router_with_multiple_conditions():
"""Test a router that triggers when any of multiple steps complete (OR condition),
and another router that triggers only after all specified steps complete (AND condition).

15
tests/llm_test.py
View File

@@ -1,3 +1,5 @@
from time import sleep
import pytest
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
@@ -5,24 +7,31 @@ from crewai.llm import LLM
from crewai.utilities.token_counter_callback import TokenCalcHandler
# TODO: This test fails without print statement, which makes me think that something is happening asynchronously that we need to eventually fix and dive deeper into at a later date
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_callback_replacement():
llm = LLM(model="gpt-4o-mini")
llm1 = LLM(model="gpt-4o-mini")
llm2 = LLM(model="gpt-4o-mini")
calc_handler_1 = TokenCalcHandler(token_cost_process=TokenProcess())
calc_handler_2 = TokenCalcHandler(token_cost_process=TokenProcess())
llm.call(
result1 = llm1.call(
messages=[{"role": "user", "content": "Hello, world!"}],
callbacks=[calc_handler_1],
)
print("result1:", result1)
usage_metrics_1 = calc_handler_1.token_cost_process.get_summary()
print("usage_metrics_1:", usage_metrics_1)
llm.call(
result2 = llm2.call(
messages=[{"role": "user", "content": "Hello, world from another agent!"}],
callbacks=[calc_handler_2],
)
sleep(5)
print("result2:", result2)
usage_metrics_2 = calc_handler_2.token_cost_process.get_summary()
print("usage_metrics_2:", usage_metrics_2)
# The first handler should not have been updated
assert usage_metrics_1.successful_requests == 1

16
uv.lock generated
View File

@@ -720,7 +720,7 @@ requires-dist = [
{ name = "instructor", specifier = ">=1.3.3" },
{ name = "json-repair", specifier = ">=0.25.2" },
{ name = "jsonref", specifier = ">=1.1.0" },
{ name = "litellm", specifier = ">=1.44.22" },
{ name = "litellm", specifier = "==1.57.4" },
{ name = "mem0ai", marker = "extra == 'mem0'", specifier = ">=0.1.29" },
{ name = "openai", specifier = ">=1.13.3" },
{ name = "openpyxl", specifier = ">=3.1.5" },
@@ -2344,24 +2344,24 @@ wheels = [
[[package]]
name = "litellm"
version = "1.50.2"
version = "1.57.4"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "aiohttp" },
{ name = "click" },
{ name = "httpx" },
{ name = "importlib-metadata" },
{ name = "jinja2" },
{ name = "jsonschema" },
{ name = "openai" },
{ name = "pydantic" },
{ name = "python-dotenv" },
{ name = "requests" },
{ name = "tiktoken" },
{ name = "tokenizers" },
]
sdist = { url = "https://files.pythonhosted.org/packages/a7/45/4d54617b267a96f1f7c17c0010ea1aba20e30a3672b873fe92a6001e5952/litellm-1.50.2.tar.gz", hash = "sha256:b244c9a0e069cc626b85fb9f5cc252114aaff1225500da30ce0940f841aef8ea", size = 6096949 }
sdist = { url = "https://files.pythonhosted.org/packages/1a/9a/115bde058901b087e7fec1bed4be47baf8d5c78aff7dd2ffebcb922003ff/litellm-1.57.4.tar.gz", hash = "sha256:747a870ddee9c71f9560fc68ad02485bc1008fcad7d7a43e87867a59b8ed0669", size = 6304427 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/22/f3/89a4d65d1b9286eb5ac6a6e92dd93523d92f3142a832e60c00d5cad64176/litellm-1.50.2-py3-none-any.whl", hash = "sha256:99cac60c78037946ab809b7cfbbadad53507bb2db8ae39391b4be215a0869fdd", size = 6318265 },
{ url = "https://files.pythonhosted.org/packages/9f/72/35c8509cb2a37343c213b794420405cbef2e1fdf8626ee981fcbba3d7c5c/litellm-1.57.4-py3-none-any.whl", hash = "sha256:afe48924d8a36db801018970a101622fce33d117fe9c54441c0095c491511abb", size = 6592126 },
]
[[package]]
@@ -3155,7 +3155,7 @@ wheels = [
[[package]]
name = "openai"
version = "1.52.1"
version = "1.59.6"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "anyio" },
@@ -3167,9 +3167,9 @@ dependencies = [
{ name = "tqdm" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/80/ac/54c76352d493866637756b7c0ecec44f0b5bafb8fe753d98472cf6cfe4ce/openai-1.52.1.tar.gz", hash = "sha256:383b96c7e937cbec23cad5bf5718085381e4313ca33c5c5896b54f8e1b19d144", size = 310069 }
sdist = { url = "https://files.pythonhosted.org/packages/2e/7a/07fbe7bdabffd0a5be1bfe5903a02c4fff232e9acbae894014752a8e4def/openai-1.59.6.tar.gz", hash = "sha256:c7670727c2f1e4473f62fea6fa51475c8bc098c9ffb47bfb9eef5be23c747934", size = 344915 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/ad/31/28a83e124e9f9dd04c83b5aeb6f8b1770f45addde4dd3d34d9a9091590ad/openai-1.52.1-py3-none-any.whl", hash = "sha256:f23e83df5ba04ee0e82c8562571e8cb596cd88f9a84ab783e6c6259e5ffbfb4a", size = 386945 },
{ url = "https://files.pythonhosted.org/packages/70/45/6de8e5fd670c804b29c777e4716f1916741c71604d5c7d952eee8432f7d3/openai-1.59.6-py3-none-any.whl", hash = "sha256:b28ed44eee3d5ebe1a3ea045ee1b4b50fea36ecd50741aaa5ce5a5559c900cb6", size = 454817 },
]
[[package]]