Mistral-7B-UA-Grammar-GRPO / README.md

thedanmaks

Trained with Unsloth

0713229 verified about 1 month ago

preview code

raw

history blame contribute delete

628 Bytes

metadata

base_model: SherlockAssistant/Mistral-7B-Instruct-Ukrainian
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
  - trl
  - grpo
license: apache-2.0
language:
  - en

Uploaded model

Developed by: thedanmaks
License: apache-2.0
Finetuned from model : SherlockAssistant/Mistral-7B-Instruct-Ukrainian

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.