VAGOsolutions
/

SauerkrautLM-Mixtral-8x7B-Instruct

Text Generation

Mixture of Experts

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Document/publish the training data and training procedure

#7

by kno10 - opened Jun 11

kno10

Jun 11

It would be important to document:

how much data was used for finetuning
how many samples for for DPO
mixture of training data (in particular, languages)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment