Highlights
- Pro
Starred repositories
LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
React Starter Kit built using React Router v7, Clerk, Convex & Polar
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
GGUF Quantization support for native ComfyUI models
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
A curated list of resources for using LLMs to develop more competitive grant applications.
Official inference repo for FLUX.1 models
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
Tool for onnx->keras or onnx->tflite. Hope this tool can help you.
[EMNLP Findings 2024] MobileQuant: Mobile-friendly Quantization for On-device Language Models
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
Visualization of cache-optimized matrix multiplication
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
A Survey of Hallucination in Large Foundation Models
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
An open source implementation of CLIP.
An open-source framework for training large multimodal models.