hugpadhugpad

RedHatAI / Meta-Llama-3.1-70B-Instruct-FP8

Text Generation71B140K52Updated Mar 25, 2025
Hugging Face

Downloads

140K

Likes

52

Last updated

Mar 25, 2025

License

llama3.1

Quantized version of Meta-Llama-3.1-70B-Instruct. It achieves an average score of 84.29 on the OpenLLM benchmark (version 1), whereas the unquantized model achieves 84.40.

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • llama
  • text-generation
  • fp8
  • vllm
  • conversational

Technical specifications

Parameters71B
Librarytransformers
Languages8 languages
Base modelmeta-llama/Meta-Llama-3.1-70B-Instruct
Licensellama3.1