Pinned Repositories
Chinese-LLaMA-Alpaca-2
中文LLaMA-2 & Alpaca-2大语言模型 (Chinese LLaMA-2 & Alpaca-2 LLMs)
Chinese-LlaMA2
Repo for adapting Meta LlaMA2 in Chinese! META最新发布的LlaMA2的汉化版! (完全开源可商用)
llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
Llama2-Chinese
Llama中文社区,最好的中文Llama大模型,完全开源可商用
llama_fork
Inference code for LLaMA models
LLM-Agent-Survey
AI agents综述,包含agents的构建,应用和评估策略(多个评估基准,agent bench也在内)
MNBVC
MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化,也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
self-instruct
Aligning pretrained language models with instruction data generated by themselves.
SuperCLUE-Math6
SuperCLUE-Math6:新一代中文数学推理数据集的探索之旅
HangXue-lab's Repositories
HangXue-lab/Chinese-LLaMA-Alpaca-2
中文LLaMA-2 & Alpaca-2大语言模型 (Chinese LLaMA-2 & Alpaca-2 LLMs)
HangXue-lab/Chinese-LlaMA2
Repo for adapting Meta LlaMA2 in Chinese! META最新发布的LlaMA2的汉化版! (完全开源可商用)
HangXue-lab/llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
HangXue-lab/Llama2-Chinese
Llama中文社区,最好的中文Llama大模型,完全开源可商用
HangXue-lab/llama_fork
Inference code for LLaMA models
HangXue-lab/LLM-Agent-Survey
AI agents综述,包含agents的构建,应用和评估策略(多个评估基准,agent bench也在内)
HangXue-lab/MNBVC
MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化,也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。
HangXue-lab/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
HangXue-lab/self-instruct
Aligning pretrained language models with instruction data generated by themselves.
HangXue-lab/SuperCLUE-Math6
SuperCLUE-Math6:新一代中文数学推理数据集的探索之旅