pytorch

Chinese-LLaMA-2-LoRA-7B-64K WARNING: LoRA model cannot be used alone. This repository contains Chine

使用DPO数据(只使用中文部分训练，长对话偏好) DPO-EN-ZH-20k 包含大量偏好对齐的问答对数据，有助于进一步提升chat模型的对话质量，使其生成内容更加详细、适合人类偏好。

Chinese-Alpaca-Pro-LoRA-7B This repo contains the tokenizer, Chinese-Alpaca LoRA weights and configs

Chinese-Alpaca-2-LoRA-13B This is the LoRA model for Chinese-Alpaca-2-13B，which should be merged wit

Chinese-Alpaca-Plus-LoRA-7B This repo contains the tokenizer, Chinese-Alpaca LoRA weights and config

Chinese-LLaMA-2-LoRA-13B-16K This is the LoRA model for Chinese-LLaMA-2-13B-16K (context size 16K)，w

Chinese-Alpaca-Pro-LoRA-13B This repo contains the tokenizer, Chinese-Alpaca LoRA weights and config

Chinese-Alpaca-2-1.3B-RLHF This repository contains Chinese-Alpaca-2-1.3B-RLHF, which is tuned on Ch

Chinese-Alpaca-Plus-LoRA-13B This repo contains the tokenizer, Chinese-Alpaca LoRA weights and confi

Chinese-LLaMA-2-LoRA-13B This is the LoRA model for Chinese-LLaMA-2-13B，which should be merged with

Chinese-Alpaca-2-LoRA-7B-64K WARNING: LoRA model cannot be used alone. This repository contains Chin

Chinese-LLaMA-2-LoRA-7B-16K This is the LoRA model for Chinese-LLaMA-2-7B-16K (context size 16K)，whi

Chinese-Alpaca-2-LoRA-13B-16K This is the LoRA model for Chinese-Alpaca-2-13B-16K (context size 16K)

Chinese-LLaMA-2-LoRA-7B This is the LoRA model for Chinese-LLaMA-2-7B，which should be merged with or

当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 SDK下载 #安装ModelS

Chinese-Alpaca-2-LoRA-7B This is the LoRA model for Chinese-Alpaca-2-7B，which should be merged with

Chinese-Alpaca-2-LoRA-7B-16K This is the LoRA model for Chinese-Alpaca-2-7B-16K (context size 16K)，w

Chinese-Alpaca-Plus-LoRA-33B This repo contains the tokenizer, Chinese-Alpaca LoRA weights and confi

Chinese-Alpaca-Pro-LoRA-33B This repo contains the tokenizer, Chinese-Alpaca LoRA weights and config

Chinese-Alpaca-2-7B-RLHF This repository contains Chinese-Alpaca-2-7B-RLHF, which is tuned on Chines