-
Notifications
You must be signed in to change notification settings - Fork 398
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
Add support for DBRX #623
base: main
Are you sure you want to change the base?
Add support for DBRX #623
Conversation
@LaaZa I will test this. |
@LaaZa The quantize process is not working. The end result is 243G which is != pre-quant/8. Also the quantize speed is of ~20 minutes is too fast for model of this size. |
Print of dbrx-instruct.modules
|
Due to the unusual architechture of the MoE implementation, the original model seems to not quantize. There are ways to convert it to something that more likely works, but that requires slightly different version than what this PR currently has. I'll keep this updated according to what is most beneficial way forward, but I would say to wait for support in transformers, so we have a more standardized goal. |
Perfect, thanks. Please let me know if I still can test something |
Hi @Qubitium PS: I made a short doc for anyone else who wanted to quickly test these models: https://gist.github.com/maziyarpanahi/e2e005addef6bb9ca97f9ff6c4c4f0d5 |
# Conflicts: # auto_gptq/modeling/__init__.py # auto_gptq/modeling/_const.py # auto_gptq/modeling/auto.py
I think this is ready for retesting with transformers 4.40.0 |
Adds support for databricks/dbrx
NOT tested, way too big for me to test and the tiny dummy model yujiepan/dbrx-tiny-random has too small infeatures.
If possbile please test and report here.
Requirestrust_remote_code=True
andtiktoken
packageRequires
transformers>=4.40.0
Closes #621