michael-wzhu / PromptCBLUELinks
PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese
☆390Updated 2 years ago
Alternatives and similar repositories for PromptCBLUE
Users that are interested in PromptCBLUE are comparing it to the libraries listed below
Sorting:
- A Chinese medical ChatGPT based on LLaMa, training from large-scale pretrain corpus and multi-turn dialogue dataset.☆385Updated 2 years ago
- CMB, A Comprehensive Medical Benchmark in Chinese☆228Updated 10 months ago
- Deepspeed、LLM、Medical_Dialogue、医疗大模型、预训练、微调☆290Updated last year
- The Largest-scale Chinese Medical QA Dataset： with 26,000,000 question answer pairs.☆315Updated last year
- 🛰️ 基于真实医疗对话数据在ChatGLM上进行LoRA、P-Tuning V2、Freeze、RLHF等微调，我们的眼光不止于医疗问答☆339Updated 2 years ago
- 各大顶会医疗领域NLP论文与资源。NLP papers and resources in the medical field.☆116Updated 2 years ago
- Taiyi 2, Biomedical LLM, A Bilingual (Chinese and English) Fine-Tuned Large Language Model for Diverse Biomedical Tasks☆165Updated 6 months ago
- This is updated version of the dataset for Chinese community medical question answering.☆371Updated 7 years 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)☆313Updated last year
- Repository of DISC-MedLLM, it is a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful me…☆560Updated 2 years ago
- This is the repo of the medical dialogue dataset 'imcs21' in CBLUE@Tianchi☆108Updated 3 years ago
- ☆58Updated last month
- A large Chinese Medical CQA☆68Updated 2 years 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.☆257Updated 2 years ago
- ☆109Updated last year
- Universal information extraction with instruction learning☆392Updated 11 months ago
- llm-medical-data:用于大模型微调训练的医疗数据集☆137Updated 2 years ago
- 活字通用大模型☆391Updated last year
- 开源SFT数据集整理,随时补充☆570Updated 2 years 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。☆126Updated 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）。☆358Updated 2 years ago
- ChatMed: 中文医疗大模型，善于在线回答患者/用户的日常医疗相关问题！☆609Updated 2 years ago
- ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。☆402Updated 2 years ago
- [CBLUE1] 中文医疗信息处理基准CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark☆830Updated 2 years ago
- 语言模型中文认知能力分析☆236Updated 2 years ago
- 基于ChatGLM-6B的中文问诊模型☆828Updated 2 years 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。☆223Updated 2 years 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…☆216Updated 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。☆638Updated last year
- Baichuan2代码的逐行解析版本，适合小白☆213Updated 2 years ago