中文Mixtral大模型 v1.1
本次更新主要有以下两点:
-
添加中文Mixtral技术报告,介绍了模型训练方法和相关实验分析
-
添加了预训练和指令精调训练脚本
What's Changed
- Add eval scripts by @iMountTai in #5
- Update readme and add requirements by @iMountTai in #7
- llama.cpp: add IQ3_XXS quantization models by @ymcui in #8
- Add training scripts by @iMountTai in #18
- Add Chinese Mixtral paper by @ymcui in #20
Full Changelog: v1.0...v1.1