Aaronhuang-778

Lumina-mGPT

torchchat

Run PyTorch LLMs locally on servers, desktop and mobile

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

unmet-promise

Code repository for the paper "The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better"

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

vmoe

lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

flash-attention

Fast and memory-efficient exact attention

SNNGX_qSNN_encryption

LLaVA-NeXT

LayerMerge

Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML'24)

larq

An Open-Source Library for Training Binarized Neural Networks

ChatTTS

A generative speech model for daily dialogue.

EdgeDeviceLLMCompetition-Starting-Kit

BGEMM-CUDA

This is a repository of Binary General Matrix Multiply (BGEMM) by customized CUDA kernel. Thank FP6-LLM for the wheels!

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

ToMe

A method to increase the speed and lower the memory footprint of existing vision transformers.

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型

outlines

Structured Text Generation

malaysian-dataset

We gather Malaysian dataset! https://malaysian-dataset.readthedocs.io/

DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

chameleon

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

mistral-inference

Official inference library for Mistral models

LLM-QAT

Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"

Quest

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

moe-quantization

Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

hf-daily-paper-newsletter-chinese

HF🤗每日简报机器人