Asmit Ganguly

``` import os from crewai import Agent, Task, Crew, Process # You can choose to use a local model through Ollama for example. # In this case we will use...

Adding support to Llama 3.1

2

As llama 2 and llama 3.1 are quite similar in terms of architecture hence, will it be possible to add support for llama 3.1?

Benchmark on MPS device (Apple silicon)

2

The results of the benchmark are not including the apple metal performance.

### Reminder - [x] I have read the above rules and searched the existing issues. ### Description Please provide the support for smolvlm [HuggingFaceTB/SmolVLM-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct) ### Pull Request _No response_