New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support CohereForAI/c4ai-command-r-v01 #480

Closed

choyakawa opened this issue Mar 14, 2024 · 1 comment

choyakawa commented Mar 14, 2024

It is almost llama, except: logits_scale and different DecoderLayer

see Lightning-AI/litgpt#1089 ggerganov/llama.cpp#6033

Collaborator

LZHgrla commented Mar 15, 2024

In my opinion, you can directly use CohereForAI/c4ai-command-r-v01 in xtuner.

Just like the modification on #429

Apply CohereForAI/c4ai-command-r-v01 in your config, that is pretrained_model_name_or_path = 'CohereForAI/c4ai-command-r-v01'
Expand the PROMPT_TEMPLATE according to the model and use it in your config, that is prompt_template = PROMPT_TEMPLATE.xxx

You can try it and if you encounter any problems, feel free to post them on this issue.

choyakawa closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment