I try to learn the basics of smolagents and I got the following big problem - please help! I am getting the message that I have run out of the free tier for HfApiModel, and I need to buy the paid tier. How can I use the local model to run with my CodeAgent in smolagents?

There are several methods, but you can use TransformersModel instead of HfApiModel and it will work. When using large models, powerful GPUs are required, so please be careful. Well, I think SmolLM below will work with about 1GB of VRAM… Also, Ollama is faster and uses less VRAM, but I think it will…

I tried to run the following code: from smolagents import TransformersModel from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel model = TransformersModel(model_id="HuggingFaceTB/SmolLM-135M-Instruct") agent = CodeAgent(tools=[], model=model, additional_authorized_imports=['datetime'…

from smolagents import CodeAgent, TransformersModel model = TransformersModel(model_id="HuggingFaceTB/SmolLM-135M-Instruct") agent = CodeAgent(tools=[], model=model, additional_authorized_imports=['datetime'], add_base_tools=True) agent.run( """ Alfred needs to prepare for the party. Here …

Uff ok, CodeAgent is not good with “HuggingFaceTB/SmolLM-135M-Instruct” model. As far as I understand, the reason is that the context window is too small for the default huge prompt of the CodeAgent. So I tried to use another kind of agent - ToolCallingAgent: from smolagents import DuckDuckGoSearch…

My local environment is Python 3.9, so smolagents doesn’t work locally…:sob: Anyway, I forgot about that bug, or rather, that feature… [BUG] Running with `TransformersModel` does not work opened 11:48AM - 29 Jan 25 UTC (UTC) …

Good code example for using Ollama with smolagents. [image] How to run agents from `smolagents` locally? Inference Endpoints on the Hub I have been running everything locally by using either the TransfomerModel or MLXModel classes instead of the HfApiModel class. from smo…

I just posted another solution in the course category, check it out here. This way you’re not tied only to local inference if you don’t have a beefy machine. Alternative options for API endpoints

Avoiding the usage of HfApiModel and using local model - `smolagents`

Beginners

John6666 May 2, 2025, 8:16pm 7

Good code example for using Ollama with smolagents.

Topic		Replies	Views
Not clear about how to run the agent locally Beginners	1	131	May 6, 2025
How to run agents from `smolagents` locally? Inference Endpoints on the Hub	4	1567	May 27, 2025
I ran the notebook Building Agents That Use Code and it says I do not have free inference time Course	1	80	May 21, 2025
How to deploy smolagents locally Beginners	2	304	April 28, 2025
SmolAgents: Try to run Agent with local model (mistral) Beginners	3	782	March 24, 2025

Avoiding the usage of HfApiModel and using local model - `smolagents`

Related topics