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

Fix docstrings of models (#344)

This commit is contained in:
Albert Villanova del Moral 2025-01-24 14:23:24 +01:00 committed by GitHub
parent 0217d3fd58
commit 2a2b76487b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/smolagents/models.py
View File

@ -309,6 +309,8 @@ class HfApiModel(Model):
If not provided, the class will try to use environment variable 'HF_TOKEN', else use the token stored in the Hugging Face CLI configuration. If not provided, the class will try to use environment variable 'HF_TOKEN', else use the token stored in the Hugging Face CLI configuration.
timeout (`int`, *optional*, defaults to 120): timeout (`int`, *optional*, defaults to 120):
Timeout for the API request, in seconds. Timeout for the API request, in seconds.
**kwargs:
Additional keyword arguments to pass to the Hugging Face API.
Raises: Raises:
ValueError: ValueError:
@ -382,10 +384,10 @@ class TransformersModel(Model):
The device_map to initialize your model with. The device_map to initialize your model with.
torch_dtype (`str`, *optional*): torch_dtype (`str`, *optional*):
The torch_dtype to initialize your model with. The torch_dtype to initialize your model with.
trust_remote_code (bool): trust_remote_code (bool, default `False`):
Some models on the Hub require running remote code: for this model, you would have to set this flag to True. Some models on the Hub require running remote code: for this model, you would have to set this flag to True.
kwargs (dict, *optional*): **kwargs:
Any additional keyword arguments that you want to use in model.generate(), for instance `max_new_tokens` or `device`. Additional keyword arguments to pass to `model.generate()`, for instance `max_new_tokens` or `device`.
Raises: Raises:
ValueError: ValueError:
If the model name is not provided. If the model name is not provided.
@ -552,9 +554,9 @@ class LiteLLMModel(Model):
Parameters: Parameters:
model_id (`str`): model_id (`str`):
The model identifier to use on the server (e.g. "gpt-3.5-turbo"). The model identifier to use on the server (e.g. "gpt-3.5-turbo").
api_base (`str`): api_base (`str`, *optional*):
The base URL of the OpenAI-compatible API server. The base URL of the OpenAI-compatible API server.
api_key (`str`): api_key (`str`, *optional*):
The API key to use for authentication. The API key to use for authentication.
**kwargs: **kwargs:
Additional keyword arguments to pass to the OpenAI API. Additional keyword arguments to pass to the OpenAI API.
@ -626,7 +628,7 @@ class OpenAIServerModel(Model):
The base URL of the OpenAI-compatible API server. The base URL of the OpenAI-compatible API server.
api_key (`str`, *optional*): api_key (`str`, *optional*):
The API key to use for authentication. The API key to use for authentication.
custom_role_conversions (`Dict{str, str]`, *optional*): custom_role_conversions (`dict[str, str]`, *optional*):
Custom role conversion mapping to convert message roles in others. Custom role conversion mapping to convert message roles in others.
Useful for specific models that do not support specific message roles like "system". Useful for specific models that do not support specific message roles like "system".
**kwargs: **kwargs:
@ -698,7 +700,7 @@ class AzureOpenAIServerModel(OpenAIServerModel):
The API key to use for authentication. If not provided, it will be inferred from the `AZURE_OPENAI_API_KEY` environment variable. The API key to use for authentication. If not provided, it will be inferred from the `AZURE_OPENAI_API_KEY` environment variable.
api_version (`str`, *optional*): api_version (`str`, *optional*):
The API version to use. If not provided, it will be inferred from the `OPENAI_API_VERSION` environment variable. The API version to use. If not provided, it will be inferred from the `OPENAI_API_VERSION` environment variable.
custom_role_conversions (`Dict[str, str]`, *optional*): custom_role_conversions (`dict[str, str]`, *optional*):
Custom role conversion mapping to convert message roles in others. Custom role conversion mapping to convert message roles in others.
Useful for specific models that do not support specific message roles like "system". Useful for specific models that do not support specific message roles like "system".
**kwargs: **kwargs: