kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-asym
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
97360f0242bd2da8ca35bcff8407653304e8dcaa
Meta-Llama-3.1-8B-Instruct-…/README.md
ModelHub XC 97360f0242 初始化项目，由ModelHub XC社区提供模型 
Model: kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-asym
Source: Original Platform
2026-08-09 18:11:18 +08:00

726 B
Raw Blame History

language, library_name, license, tags
language library_name license tags
en
transformers cc-by-4.0
auto-gptq
AutoRound

Model Details

This is meta-llama/Meta-Llama-3.1-8B-Instruct quantized with AutoRound (asymmetric quantization) and serialized with the GPTQ format in 4-bit. The model has been created, tested, and evaluated by The Kaitchup.

Details on quantization process, evaluation, and how to use the model here: The Best Quantization Methods to Run Llama 3.1 on Your GPU

  • Developed by: The Kaitchup
  • Language(s) (NLP): English
  • License: cc-by-4.0