Miraclemarvel55 / ChatGLM-RLHFLinks
对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF
☆197Updated 2 years ago
Alternatives and similar repositories for ChatGLM-RLHF
Users that are interested in ChatGLM-RLHF are comparing it to the libraries listed below
Sorting:
- Implementation of Chinese ChatGPT☆289Updated 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.☆258Updated 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☆416Updated 2 years ago
- chatglm多gpu用deepspeed和☆410Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆402Updated 2 years ago
- ☆314Updated 2 years ago
- alpaca中文指令微调数据集☆396Updated 2 years ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆110Updated 2 years ago
- deep learning☆149Updated 8 months 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。☆221Updated 2 years ago
- Baichuan-13B 指令微调☆90Updated 2 years ago
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated 2 years ago
- ☆282Updated last year
- 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☆165Updated 2 years ago
- A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Huma…☆140Updated 2 years 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。☆126Updated 10 months ago
- deepspeed+trainer简单高效实现多卡微调大模型☆131Updated 2 years ago
- pCLUE: 1000000+多任务提示学习数据集☆506Updated 3 years ago
- 语言模型中文认知能力分析☆236Updated 2 years ago
- ChatGLM-6B 指令学习|指令数据|Instruct☆655Updated 2 years ago
- ChatGLM-6B fine-tuning.☆137Updated 2 years ago
- ☆164Updated 2 years ago
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆262Updated last year
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆239Updated 2 years ago
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆389Updated 2 years ago
- Baichuan2代码的逐行解析版本,适合小白☆213Updated 2 years ago
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆89Updated 2 years ago
- 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)。☆358Updated 2 years ago
- A Chinese Open-Domain Dialogue System☆327Updated 2 years ago
- 微调ChatGLM☆128Updated 2 years ago