git-cloner / llama2-lora-fine-tuning
llama2 finetuning with deepspeed and lora
☆174Updated last year
Alternatives and similar repositories for llama2-lora-fine-tuning:
Users that are interested in llama2-lora-fine-tuning are comparing it to the libraries listed below
- 大语言模型指令调优工具（支持 FlashAttention）☆172Updated last year
- 怎么训练一个LLM分词器☆144Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated last year
- Large language Model fintuning bloom , opt , gpt, gpt2 ,llama,llama-2,cpmant and so on☆97Updated 11 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆358Updated 7 months ago
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆193Updated 11 months ago
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆99Updated last year
- ☆160Updated 2 years ago
- ☆96Updated last year
- ☆64Updated 2 years ago
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆192Updated last year
- deepspeed+trainer简单高效实现多卡微调大模型☆123Updated last year
- llama fine-tuning with lora☆140Updated 11 months ago
- ☆139Updated last year
- A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Huma…☆134Updated last year
- ☆278Updated 11 months ago
- Implementation of Chinese ChatGPT☆287Updated last year
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆78Updated 5 months ago
- ☆107Updated 5 months ago
- 简单易懂的LLaMA微调指南。☆398Updated last year
- 使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。☆117Updated last year
- 使用单个24G显卡，从0开始训练LLM☆53Updated 5 months ago
- ☆308Updated 2 years ago
- Naive Bayes-based Context Extension☆326Updated 4 months ago
- [EMNLP 2023] Lion: Adversarial Distillation of Proprietary Large Language Models☆205Updated last year
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆251Updated last year
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆215Updated last year
- 大模型多维度中文对齐评测基准 (ACL 2024)☆375Updated 8 months ago
- 中文 Instruction tuning datasets☆128Updated last year
- 用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.☆249Updated last year