ChenMnZ

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Pretrained-Language-Model

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

TSLD

[NeurIPS 2023] Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

QLLM

A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ, and export to onnx/onnx-runtime easily.

BitNet-Transformers

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

bitnet158

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

LLaVA-HR

LLaVA-HR: High-Resolution Large Language-Vision Assistant

StableLM

StableLM: Stability AI Language Models

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

open_clip

An open source implementation of CLIP.

minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

AnimateDiff

Official implementation of AnimateDiff.

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

PySceneDetect

:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

generative-models

Generative Models by Stability AI

Latte

Latte: Latent Diffusion Transformer for Video Generation.

marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Awesome-Video-Diffusion

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

AQLM

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf

I-ViT

[ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

LLMPrune-BESA

BESA is a differentiable weight pruning technique for large language models.

DCNv4

[CVPR 2024] Deformable Convolution v4

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

ChartAst

ChartAssistant is a chart-based vision-language model for universal chart comprehension and reasoning.

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

MM-Vet

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities (ICML 2024)