-
Notifications
You must be signed in to change notification settings - Fork 915
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.
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
MPT support #290
Comments
Probably a related issue: huggingface/transformers#23174 |
any plan on supporting mosaicml/mpt-30b-instruct support |
I am also interested in deploying the |
Yes I am also interested in getting support for MPT models. I would love to assist in any way I can. |
+1 |
please🙏 |
Hey wanna work on the implementation then we can do a pr, add me on discord mantrakp- proud Logitech controller owner |
# What does this PR do? This adds a non flash version of MPT. Flash is harder because we need to create a bias ready cuda kernel of flash attention. Fixes huggingface/text-generation-inference#361 Fixes huggingface/text-generation-inference#491 Fixes huggingface/text-generation-inference#290
# What does this PR do? This adds a non flash version of MPT. Flash is harder because we need to create a bias ready cuda kernel of flash attention. Fixes huggingface/text-generation-inference#361 Fixes huggingface/text-generation-inference#491 Fixes huggingface/text-generation-inference#290
# What does this PR do? This adds a non flash version of MPT. Flash is harder because we need to create a bias ready cuda kernel of flash attention. Fixes huggingface/text-generation-inference#361 Fixes huggingface/text-generation-inference#491 Fixes huggingface/text-generation-inference#290
Model description
Can you add a new MPT model? This looks very promising, especially the ability to extend context length by up to 85K tokens.
Open source status
Provide useful links for the implementation
https://github.com/mosaicml/llm-foundry
The text was updated successfully, but these errors were encountered: