FlagOpen / FlagData
☆263Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for FlagData
- 大模型多维度中文对齐评测基准 (ACL 2024)☆330Updated 2 months ago
- 开源SFT数据集整理,随时补充☆440Updated last year
- 语言模型中文认知能力分析☆235Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆209Updated last year
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆231Updated this week
- 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.☆241Updated last year
- ☆158Updated 11 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。☆463Updated 6 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)☆269Updated 3 months ago
- Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder☆497Updated last week
- 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 last year
- 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.☆171Updated 2 months ago
- CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models☆236Updated last week
- 大语言模型指令调优工具(支持 FlashAttention)☆166Updated 10 months ago
- Train a Chinese LLM From 0 by Personal☆197Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆121Updated 10 months ago
- 360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute☆234Updated 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…☆166Updated 5 months ago
- 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。☆160Updated 2 weeks ago
- 中文原生检索增强生成测评基准☆98Updated 6 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。☆111Updated last month
- This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.☆353Updated 6 months ago
- ☆157Updated last year
- ☆168Updated 10 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。☆202Updated 11 months ago
- [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus☆168Updated this week
- ☆297Updated last year
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆338Updated 11 months ago
- ☆213Updated 5 months ago
- FlagEval is an evaluation toolkit for AI large foundation models.☆299Updated 3 months ago