Stars
Official inference library for Mistral models
Fast and memory-efficient exact attention
UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition
A Comprehensive Toolkit for High-Quality PDF Content Extraction
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
A Python library to extract tabular data from PDFs
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…
AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓,同时包含工作和科研过程中的新想法、新问题、新资源与新项目
LlamaIndex is a data framework for your LLM applications
A high-throughput and memory-efficient inference and serving engine for LLMs
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
User-friendly WebUI for LLMs (Formerly Ollama WebUI)
A modular graph-based Retrieval-Augmented Generation (RAG) system
MTEB: Massive Text Embedding Benchmark
PubMedQA: A Dataset for Biomedical Research Question Answering
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
Accessible large language models via k-bit quantization for PyTorch.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)