Upload transformers version

#3
by ArthurZ HF staff - opened
No description provided.
ArthurZ changed pull request status to open
pandora-s changed pull request status to merged

Converted model does not work for now let me check!

Bias were missing for the multimodal projection layers

They seem to still be missing?

image.png

@pandora-s
When you updated mistralai/Mistral-Nemo-Instruct-2407 2 weeks ago, it looks like you broke it. Can you please see about fixing it for everyone? Thanks

deleted

@pandora-s
When you updated mistralai/Mistral-Nemo-Instruct-2407 2 weeks ago, it looks like you broke it. Can you please see about fixing it for everyone? Thanks

Geesh, you going to spam all of HF with this?

Any updates @ArthurZ ?

The safetensors are still not working properly.

I Quantised it to 4bit in MLX and it doesn’t spit out proper English

Converted model does not work for now let me check!

@ArthurZ Any updates on this?

Sign up or log in to comment