chaoswork / sft_datasets
开源SFT数据集整理,随时补充
☆474Updated last year
Alternatives and similar repositories for sft_datasets:
Users that are interested in sft_datasets are comparing it to the libraries listed below
- 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☆403Updated 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
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆382Updated 8 months ago
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆982Updated 8 months ago
- 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。☆518Updated 8 months ago
- 活字通用大模型☆363Updated 4 months ago
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Updated last year
- ☆276Updated 8 months ago
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆397Updated 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。☆207Updated last year
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆255Updated last month
- 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…☆183Updated 8 months ago
- 该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记(多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT)☆284Updated 9 months ago
- 语言模型中文认知能力分析☆236Updated last year
- ☆290Updated 7 months ago
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆283Updated 5 months ago
- chatglm多gpu用deepspeed和☆404Updated 6 months ago
- Baichuan2代码的逐行解析版本,适合小白☆211Updated last year
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆243Updated 7 months ago
- Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型,支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.☆516Updated 6 months ago
- unified embedding model☆847Updated last year
- 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.☆247Updated last year
- 大模型多维度中文对齐评测基准 (ACL 2024)☆353Updated 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)☆282Updated 5 months ago
- pCLUE: 1000000+多任务提示学习数据集☆475Updated 2 years ago
- PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese☆334Updated 11 months ago
- CMMLU: Measuring massive multitask language understanding in Chinese☆716Updated last month
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆344Updated 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.☆585Updated this week
- 面向中文大模型价值观的评估与对齐研究☆489Updated last year