sunzeyeah / RLHFLinks
Implementation of Chinese ChatGPT
☆287Updated last year
Alternatives and similar repositories for RLHF
Users that are interested in RLHF are comparing it to the libraries listed below
Sorting:
- alpaca中文指令微调数据集☆392Updated 2 years ago
- ☆308Updated 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☆194Updated 2 years ago
- Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆410Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆654Updated 2 years ago
- ☆280Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆495Updated 2 years ago
- chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu☆164Updated last year
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆261Updated 5 months ago
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆236Updated 2 years ago
- 语言模型中文认知能力分析☆236Updated last year
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated 2 years ago
- chatglm多gpu用deepspeed和☆408Updated 10 months ago
- ☆459Updated 11 months ago
- deep learning☆149Updated 3 weeks ago
- ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。☆399Updated last year
- 专注于中文领域大语言模型，落地到某个行业某个领域，成为一个行业大模型、公司级别或行业级别领域 大模型。☆118Updated 2 months ago
- 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.☆251Updated last year
- 中文 Instruction tuning datasets☆131Updated last year
- A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Huma…☆135Updated 2 years ago
- 大语言模型指令调优工具（支持 FlashAttention）☆173Updated last year
- 使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。☆360Updated last year
- 怎么训练一个LLM分词器☆149Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated last year
- ChatGLM-6B fine-tuning.☆135Updated 2 years ago
- 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。☆217Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated last year
- 开源SFT数据集整理,随时补充☆516Updated 2 years ago
- Baichuan2代码的逐行解析版本，适合小白☆214Updated last year
- 中文图书语料MD5链接☆218Updated last year