hugpadhugpad

CreitinGameplays / Mistral-Nemo-12B-R1-v0.1

Text Generation12B863Updated Aug 10, 2026
Hugging Face

Downloads

86

Likes

3

Last updated

Aug 10, 2026

License

mit

Took 96 hours to finetune on 2x Nvidia RTX A6000 with the following settings: - Batch size: 3 - Gradient accumulation steps: 1 - Epochs: 1 - Learning rate: 1e-4 - Warmup ratio: 0.1

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • mistral
  • text-generation
  • conversational
  • en

Technical specifications

Parameters12B
Librarytransformers
Languagesen
Base modelmistralai/Mistral-Nemo-Instruct-2407
Licensemit