PyTorch native finetuning library

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

tiny vision language model

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

🦜⛏️ Did you say you like data?

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

LLM training in simple, raw C/CUDA

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

中文nlp解决方案(大模型、数据、模型、训练、推理)

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Rust bindings for the Python interpreter

a simple uncertainty calculator.

An easy/swift-to-adapt PyTorch-Lighting template. 套壳模板，简单易用，稍改原来Pytorch代码，即可适配Lightning。You can translate your previous Pytorch code much easier using this template, and keep your freedom to edit a…

On-device Speech Recognition for Apple Silicon

SAM: Sharpness-Aware Minimization (PyTorch)

RAG Search API

Build resilient language agents as graphs.

LLM Finetuning with peft

Port of OpenAI's Whisper model in C/C++

Animated sprite editor & pixel art tool (Windows, macOS, Linux)

Puzzles for learning Triton

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

🎉 Modern CUDA Learn Notes with PyTorch: fp32, fp16, bf16, fp8/int8, flash_attn, sgemm, sgemv, warp/block reduce, dot, elementwise, softmax, layernorm, rmsnorm.

Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.

Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

Grok open release