KeyArgo
/
smolagents
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fixed agents.md (#164) 

Fix docs: custom_model should return an object that has a .content attribute
This commit is contained in:
sid tuladhar 2025-01-13 23:21:51 +08:00 committed by GitHub
parent 695d303401
commit 60b1abdae6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/source/en/reference/agents.md
View File

@ -65,7 +65,7 @@ You could use any `model` callable for your agent, as long as:
1. It follows the [messages format](./chat_templating) (`List[Dict[str, str]]`) for its input `messages`, and it returns a `str`. 1. It follows the [messages format](./chat_templating) (`List[Dict[str, str]]`) for its input `messages`, and it returns a `str`.
2. It stops generating outputs *before* the sequences passed in the argument `stop_sequences` 2. It stops generating outputs *before* the sequences passed in the argument `stop_sequences`
For defining your LLM, you can make a `custom_model` method which accepts a list of [messages](./chat_templating) and returns text. This callable also needs to accept a `stop_sequences` argument that indicates when to stop generating. For defining your LLM, you can make a `custom_model` method which accepts a list of [messages](./chat_templating) and returns an object with a .content attribute containing the text. This callable also needs to accept a `stop_sequences` argument that indicates when to stop generating.
```python ```python
from huggingface_hub import login, InferenceClient from huggingface_hub import login, InferenceClient
@ -76,9 +76,9 @@ model_id = "meta-llama/Llama-3.3-70B-Instruct"
client = InferenceClient(model=model_id) client = InferenceClient(model=model_id)
def custom_model(messages, stop_sequences=["Task"]) -> str: def custom_model(messages, stop_sequences=["Task"]):
response = client.chat_completion(messages, stop=stop_sequences, max_tokens=1000) response = client.chat_completion(messages, stop=stop_sequences, max_tokens=1000)
answer = response.choices[0].message.content answer = response.choices[0].message
return answer return answer
``` ```
@ -140,4 +140,4 @@ model = LiteLLMModel("anthropic/claude-3-5-sonnet-latest", temperature=0.2)
print(model(messages, max_tokens=10)) print(model(messages, max_tokens=10))
``` ```
[[autodoc]] LiteLLMModel [[autodoc]] LiteLLMModel