FlagOpen / FlagData
☆299Updated 8 months ago
Alternatives and similar repositories for FlagData:
Users that are interested in FlagData are comparing it to the libraries listed below
- 开源SFT数据集整理,随时补充☆491Updated last year
- 语言模型中文认知能力分析☆236Updated last year
- 大模型多维度中文对齐评测基准 (ACL 2024)☆363Updated 6 months ago
- Baichuan2代码的逐行解析版本,适合小白☆212Updated 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☆406Updated last year
- 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)☆289Updated 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
- CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models☆275Updated 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.☆213Updated 2 months ago
- Alpaca Chinese Dataset -- 中文指令微调数据集☆192Updated 4 months ago
- 中文原生检索增强生成测评基准☆111Updated 10 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…☆186Updated 9 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆169Updated 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。☆535Updated 10 months ago
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆399Updated 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。☆211Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆131Updated 2 months ago
- 活字通用大模型☆382Updated 5 months ago
- ☆162Updated last year
- ☆159Updated last year
- 360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute☆267Updated 5 months ago
- SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding☆218Updated last year
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆503Updated this week
- FinEval是一 个中文金融领域高质量多项选择与文本问答题的集合。☆173Updated 4 months ago
- chatglm多gpu用deepspeed和☆405Updated 7 months ago
- 部署你自己的OpenAI api🤩, 基于flask, transformers (使用 Baichuan2-13B-Chat-4bits 模型, 可以运行在单张Tesla T4显卡) ,实现了OpenAI中Chat, Models和Completions接口,包含流式响…☆89Updated last year
- unified embedding model☆851Updated last year
- ☆225Updated 9 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)。☆357Updated last year
- FlagEval is an evaluation toolkit for AI large foundation models.☆320Updated 7 months ago