huggingface / huggingface/agents-course

Error with meta-llama/Llama-3.2-3B-Instruct Model in Unit 1 "Dummy Agents Library" Section

Open
#487 2 comments 8 reactions 0 assignees View on GitHub
Dominant language
MDX
Stars
32.6k
Forks
2.3k
PR merge metrics
No merged PRs in 30d

Description

I am working through the "AI Agents" course, specifically in Unit 1 (Introduction to Agents). While trying to follow along with the "Dummy Agents Library" section, I encountered an issue related to model compatibility. The model meta-llama/Llama-3.2-3B-Instruct is causing the following error:
```
ValueError: Model meta-llama/Llama-3.2-3B-Instruct is not supported for task text-generation and provider together. Supported task: conversational.

```
This error indicates that the model is only suited for conversational tasks, not for text generation, as expected in this section of the course.

Steps to reproduce:

Follow the instructions in Unit 1, specifically in the "Dummy Agents Library" subsection.

Run the provided code snippet which uses the meta-llama/Llama-3.2-3B-Instruct model for text generation.

Encounter the error.

Expected behavior:
The model should be compatible with the task of text generation.

Actual behavior:
The model is incompatible, and an error message is thrown.

Possible solution (if known):
Please suggest a compatible model for text generation, or update the course material to reflect the proper model.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.