chaoswork / sft_datasets
开源SFT数据集整理,随时补充
☆413Updated last year
Related projects: ⓘ
- 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
- 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
- ChatGLM-6B 指令学习|指令数据|Instruct☆656Updated last year
- 本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。☆408Updated 4 months ago
- ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。☆395Updated last year
- 语言模 型中文认知能力分析☆234Updated last year
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆956Updated 4 months ago
- Baichuan2代码的逐行解析版本，适合小白☆208Updated 11 months ago
- pCLUE: 1000000+多任务提示学习数据集☆461Updated last year
- unified embedding model☆814Updated last year
- ☆265Updated 4 months ago
- 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
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆243Updated 6 months ago
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆328Updated 4 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。☆198Updated 9 months ago
- PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese☆316Updated 7 months ago
- chatglm多gpu用deepspeed和☆395Updated 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.☆240Updated last year
- alpaca中文指令微调数据集☆390Updated last year
- 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
- 大模型多维度中文对齐评测基准 (ACL 2024)☆292Updated last month
- Implementation of Chinese ChatGPT☆282Updated 9 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…☆159Updated 4 months ago
- 本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.☆153Updated 3 weeks ago
- ☆290Updated last year
- 活字通用大模型☆332Updated last week
- GAOKAO-Bench is an evaluation framework that utilizes GAOKAO questions as a dataset to evaluate large language models.☆516Updated 5 months ago
- 雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆255Updated last month
- Deepspeed 、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆227Updated 3 months ago
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder☆427Updated last month