bluewelkin
Follow
Stars
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction
使用深度学习方法解析问题 知识图谱存储 查询知识点 基于医疗垂直领域的对话系统
Convert any text to a graph of knowledge. This can be used for Graph Augmented Generation or Knowledge Graph based QnA
## 基于LSTM三分类的文本情感分析 ### 背景介绍 文本情感分析作为NLP的常见任务，具有很高的实际应用价值。本文将采用LSTM模型，训练一个能够识别文本postive, neutral, negative三种情感的分类器。 本文的目的是快速熟悉LSTM做情感分析任务，所以本文提到的只是一个baseline，并在最后分析了其优劣。对于真正的文本情感分析，在本文提到的模型之上，还可以做很…
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, Inter…
Label Studio is a multi-type data labeling and annotation tool with standardized output format
AIdea 是一款支持 GPT 以及国产大语言模型通义千问、文心一言等，支持 Stable Diffusion 文生图、图生图、 SDXL1.0、超分辨率、图片上色的全能型 APP。
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Attempting to make the Deep Learning Book easier to understand.
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
🔊 Text-Prompted Generative Audio Model
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
A library for efficient similarity search and clustering of dense vectors.
A knowledge graph for Chinese cookbook（中式菜谱知识图谱）
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。
The database for modern applications. Common use cases: knowledge graphs for AI, fraud detection, personalization, and search. Built and maintained by @HypermodeInc.
Advanced Multi-Turn QA System with LLM and Intent Recognition. 基于LLM大语言模型意图识别、参数抽取结合slot词槽技术实现多轮问答、NL2API. 打造Function Call多轮问答最佳实践