pany8125 / ShareGPTQAExtractor-mnbvc
MNBVC项目-ShareGPT语料清洗
☆15Updated last year
Alternatives and similar repositories for ShareGPTQAExtractor-mnbvc:
Users that are interested in ShareGPTQAExtractor-mnbvc are comparing it to the libraries listed below
- [EMNLP 2024] PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological Counseling☆13Updated 2 weeks ago
- SiliconCloud Cookbook☆19Updated 2 months ago
- ☆31Updated last year
- ☆17Updated 2 years ago
- ☆20Updated last year
- ☆19Updated last year
- 本项目主要对开源的MOSS SFT数据进行整理 ,转换成mnbvc多轮对话格式。MOSS-003涵盖用性、忠实性、无害性三个层面,共353w样本,MOSS-003 包含更细粒度的有用性类别标记、更广泛的无害性数据和更长对话轮数,共630w样本,☆11Updated last year
- ☆42Updated last year
- open-llms-next-web,一个类似于chatgpt-next-web的开源大型语言模型web演示,支持离线开源大模型和PEFT模型☆18Updated 11 months ago
- Finetune Bloom big language model with Lora method☆31Updated last year
- ☆23Updated 2 years ago
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆22Updated 10 months ago
- By leveraging Bocha AI Search API , your AI applications can now access high-quality, up-to-date knowledge from billions of web pages and…☆19Updated 3 months ago
- ☆27Updated 6 months ago
- baike schema crawler for baidu baike , hudongbaike. 面向百度百科与互动百科的概念分类体系抓取脚本☆36Updated 7 years ago
- ☆18Updated last year
- 大语言模型训练和服务调研☆37Updated last year
- 中文领域心理健康对话大模型simpsybot☆42Updated 4 months ago
- auto push daily news with ai☆12Updated this week
- Evaluation for AI apps and agent☆41Updated last year
- the newest version of llama3,source code explained line by line using Chinese☆22Updated last year
- ☆39Updated last year
- 微调阿里开源的文字检测模型,利用合合识别返回的OCR结果作为初始训练数据,对模型进行优化训练,使其更加适应1万张图片的具体场景,提高文字识别的精度。☆9Updated 5 months ago
- GoGPT中文指令数据集构造☆10Updated last year
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆46Updated 10 months ago
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆55Updated last year
- Agentica: Effortlessly Build Intelligent, Reflective, and Collaborative Multimodal AI Agents! 轻松构建智能、具备反思能力、可协作的多模态AI Agent。☆155Updated this week
- TianGong-AI-Unstructure☆64Updated 3 weeks ago
- TPO 是一个优化 LLM 输出文本的框架,通过迭代反馈和优化提示的方式来“微调模型”,而非直接调整模型的参数,使模型在推理过程中与人类偏好对齐以生成更好的结果。本项目提供了一个友好的 WebUI 来加载模型,实时优化基础模型并展示最佳结果。☆10Updated 2 months ago
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆47Updated last year