Pedro Cuenca comments

Results 331 comments of


                                            Pedro Cuenca

Add a new blog post: How to use HF endpoints to run Concrete-ML privacy-preserving ML models.

I'll be paying attention, feel free to fix and we can merge.

Add a new blog post: How to use HF endpoints to run Concrete-ML privacy-preserving ML models.

I tried to preview but couldn't, let's merge and fix later if we need to.

Add a new blog post: How to use HF endpoints to run Concrete-ML privacy-preserving ML models.

@bcm-at-zama can you open a PR to change the date to April 16?

Broken link in the PEFT blog post

cc @pacman100

Typo SDXL Optimization

cc @sayakpaul

Error when fine tuning whisper model

cc @sanchit-gandhi :)

DeepSpeed giving Assertion Error

cc @lewtun @philschmid

`hf-bitsandbytes-integration.md` Incorrect Dequantization

cc @younesbelkada

Contributing models / making it easier to load from a local directory

Completely agree, this should be the focus of an upcoming release! In my opinion, making models from the Hub discoverable from the app should be our top priority, as most...

Contributing models / making it easier to load from a local directory

We sure do! https://discord.gg/a9XpacAw After you are in you can visit the #role-assignment channel and select the Diffusers topic, and then a few channels about diffusion will show up for...