Jonas Gehring

Thanks for sharing; your checklist file seems to be an HTML page for signing into a Google account. Just to double-check, you ran `bash download.sh` and pasted the link you...

Hi @zlfeng83, Code Llama models have not be specifically trained or evaluated for function calling. However, I would think that it might be worth experimenting with it and maybe try...

I can't provide support for the quantized versions of Code Llama. Can you double-check that you get similar behavior with inference code from this repo and a model retrieved via...

Can you check whether ollama's `codellama:7b` is built from the "Code Llama" or the "Code Llama Instruct" model? If it's the former then it won't know out of the box...

Thanks! Yeah that seems to be the base model which is trained purely to continue the sequence you prompt it with. For any Q&A-style or chat scenarios, try the 7b-instruct...

You can also check the examples in `example_completion.py`, for which the base models will output sensible completions: https://github.com/facebookresearch/codellama/blob/1af62e1f43db1fa5140fa43cb828465a603a48f3/example_completion.py#L27-L39

I'll close this for now; feel free to re-open if you're still having issues with this.

Hi @aditya4d1, to rule out corrupted files (which the error message seems to point to), can you run `md5sum -c checklist.chk` in the CodeLlama-7b directory?

Hi @XinyuShe, I'm not sure what you're referring to since the repo doesn't feature a `generate()` function like the one you're describing.

Hi @jose-at-slalom, the URL from the e-mail is valid for 24 hours. Did the link already expire maybe?