sunzeyeah / RLHF
Implementation of Chinese ChatGPT
☆282Updated 9 months ago
Related projects: ⓘ
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆186Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆461Updated last year
- alpaca中文指令微调数据集☆390Updated last year
- ☆265Updated 4 months ago
- ☆290Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆656Updated 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。☆198Updated 9 months ago
- 语言模型中文认知能力分析☆234Updated 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☆396Updated 10 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.☆240Updated last year
- chatglm多gpu用deepspeed和☆395Updated 2 months ago
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆233Updated last year
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆243Updated 6 months ago
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆389Updated last year
- ☆447Updated 3 months ago
- 开源SFT数据集整理,随时补充☆413Updated last year
- deep learning☆149Updated 2 months ago
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆395Updated last year
- Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.☆562Updated 2 months 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)。☆349Updated last year
- Baichuan-13B 指令微调☆89Updated last year
- Efficient, Low-Resource, Distributed transformer implementation based on BMTrain☆233Updated 9 months ago
- A Chinese Open-Domain Dialogue System☆310Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆208Updated 11 months ago
- chatglm2 6b finetuning and alpaca finetuning☆146Updated 4 months ago
- 中文 Instruction tuning datasets☆112Updated 5 months ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆292Updated last month
- 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。☆102Updated this week
- 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…☆159Updated 4 months ago
- ☆156Updated last year