Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理，可实现 CPU 上毫秒级的 OCR 精准预测，通用场景中英文OCR达到开源SOTA。

A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.

基于知识图谱的《红楼梦》人物关系可视化及问答系统

An Open Large Reasoning Model for Real-World Solutions

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

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…

「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

Java version of LangChain, while empowering LLM for Big Data.

TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios

High-quality datasets, tools, and concepts for LLM fine-tuning.

sqldf for pandas

The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM".

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Robust recipes to align language models with human and AI preferences

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

LLM101n: Let's build a Storyteller

[ICLR2022] official implementation of UniFormer

TrustRAG：The RAG Framework within Reliable input,Trusted output

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

A Strong FuxiCTR Baseline for News CTR Challenge at RecSys 2024

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

Grok open release

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.