thunder95
Follow
Stars
A lightweight library for portable low-level GPU computation using WebGPU.
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快
Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];
Machine Learning Containers for NVIDIA Jetson and JetPack-L4T
Repository for “PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers”, NAACL24
Official repository for paper MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning(https://arxiv.org/abs/2406.17770).
This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation
Quick exploration into fine tuning florence 2
10000 chatTTS voices ！chatTTS 音色库，再也不为音色抽卡烦恼啦。这是我第一个项目，熬夜龟速生产10000条音色并上传Github，给点鼓励呗哈！主域名：https://www.TTSlist.com 备用：http:https://ttslist.aiqbh.com/
SuperSonic is the next-generation BI platform that integrates Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
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)
LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案
Multilingual Sentence & Image Embeddings with BERT
Your fully proficient, AI-powered and local chatbot assistant🤖
Multi-Joint dynamics with Contact. A general purpose physics simulator.
Data annotation toolbox supports image, audio and video data.
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
Neo4j graph construction from unstructured data using LLMs
Generate dialog data from documents using LLM like ChatGLM2 or ChatGPT;利用ChatGLM2,ChatGPT等大模型根据文档生成对话数据集
A generative speech model for daily dialogue.
OpsPilot是WeOps团队开源的一个基于深度学习与LLM技术的智能运维助理 OpsPilot is an open source intelligent operation and maintenance assistant based on deep learning and LLM technology developed by the WeOps team.
Source code for xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
微信公众号文章批量下载工具，支持图片、评论下载，支持保存html/mhtml/md/pdf/docx文件
SimPO: Simple Preference Optimization with a Reference-Free Reward