sunzeyeah / RLHF
Implementation of Chinese ChatGPT
☆287Updated last year
Related projects ⓘ
Alternatives and complementary repositories for RLHF
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆189Updated last year
- ☆273Updated 6 months ago
- alpaca中文指令微调数据集☆391Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆469Updated 2 years 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.☆242Updated last year
- ☆297Updated last year
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆388Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Updated last year
- 语言模型中文认知能力分析☆235Updated 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。☆204Updated 11 months ago
- ☆453Updated 5 months ago
- ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。☆395Updated last year
- 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☆397Updated last year
- 开源SFT数据集整理,随时补充☆445Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆106Updated last year
- 中文图书语料MD5链接☆211Updated 9 months ago
- chatglm多gpu用deepspeed和☆403Updated 4 months ago
- 中文 Instruction tuning datasets☆118Updated 7 months ago
- 大语言模型指令调优工具（支持 FlashAttention）☆166Updated 10 months 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☆163Updated last year
- deep learning☆149Updated 4 months ago
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆248Updated 8 months ago
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆234Updated 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）。☆356Updated last year
- Baichuan2代码的逐行解析版本，适合小白☆208Updated last year
- chatglm2 6b finetuning and alpaca finetuning☆144Updated 7 months ago
- 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。☆112Updated 2 months ago
- ☆157Updated last year
- A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Huma…☆126Updated last year