chaoswork / sft_datasets
开源SFT数据集整理,随时补充
☆485Updated 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☆406Updated 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.☆395Updated 9 months ago
- 语言模型中文认知能力分析☆236Updated last year
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆984Updated 9 months ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆359Updated 6 months ago
- ☆299Updated 8 months ago
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆398Updated last year
- unified embedding model☆849Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆212Updated last year
- 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…☆185Updated 9 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。☆208Updated 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。☆528Updated 9 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)☆288Updated 6 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.☆247Updated last year
- 活字通用大模型☆374Updated 5 months ago
- PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese☆339Updated last year
- ☆278Updated 9 months ago
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆256Updated 2 months ago
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Updated last year
- Train a 1B LLM with 1T tokens from scratch by personal☆532Updated this week
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆250Updated 8 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。☆298Updated 7 months ago
- ☆503Updated 8 months ago
- chatglm多gpu用deepspeed和☆405Updated 7 months ago
- CMMLU: Measuring massive multitask language understanding in Chinese☆726Updated 2 months ago
- A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.☆339Updated last year
- 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)☆291Updated 10 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。☆115Updated 5 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.☆206Updated last month