Stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
PyTorch code and models for the DINOv2 self-supervised learning method.
Utilities intended for use with Llama models.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Toolkit for large-scale whole-slide image processing.
Simultaneous Nuclear Instance Segmentation and Classification in H&E Histology Images.
When do we not need larger vision models?
Implementing DeepSeek R1's GRPO algorithm from scratch
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。
LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills
SGLang is a fast serving framework for large language models and vision language models.
Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction
TCGA Pathology Reports in Machine Readable Text
Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
The official GitHub repo for the paper MOAT: Evaluating LMMs for Capability Integration and Instruction Grounding.
A powerful tool for creating fine-tuning datasets for LLM
Official inference library for Mistral models
Official implementation of "LLaVA Needs More Knowledge: Retrieval-Augmented NLG with Knowledge Graph for Explaining Thoracic Pathologies" (AAAI 2025). This repo provides the KG-LLaVA framework, int…
An open source implementation of CLIP.
Fully open reproduction of DeepSeek-R1
An Open-source RL System from ByteDance Seed and Tsinghua AIR