NicoNico6

green-bit-llm

A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.

low_bit_llama

Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs

BNext

Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket

bitorch-engine

A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.

Deep-Learning-Interview-Book

深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

Hyper-BinaryNet

This is the code for paper "Gradients Matters: Designing Binarized Neural Network via Enhanced Infornation Flow"

lq-lora

MMS

医药管理信息系统

pytorch-tutorial

PyTorch Tutorial for Deep Learning Researchers

ShadowRemoval

An impleamention of Towards Ghost-free Shadow Removal using pytorch

NicoNico6/bitorch-engine

A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.

NicoNico6/AgentK

An autoagentic AGI that is self-evolving and modular.

NicoNico6/AQLM

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

NicoNico6/Awesome-LLM-Compression

Awesome LLM compression research papers and tools.

NicoNico6/BitBLAS

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

NicoNico6/buffer-of-thought-llm

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

NicoNico6/ChatMLX

ChatMLX is a large model real-time conversation app implemented using MLX.🚧

NicoNico6/dotai

NicoNico6/ETO

Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents

NicoNico6/evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

NicoNico6/fast-hadamard-transform

Fast Hadamard transform in CUDA, with a PyTorch interface

NicoNico6/gallama

NicoNico6/gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

NicoNico6/KIVI

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

NicoNico6/KVQuant

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

NicoNico6/langgraph

Build resilient language agents as graphs.

NicoNico6/LangGraph-Swift

🚀 LangGraph for Swift. A library for building stateful, multi-actor applications with LLMs, built to work jointly with langchain-swift

NicoNico6/llamafile

Distribute and run LLMs with a single file.

NicoNico6/lm-polygraph

NicoNico6/metal-flash-attention

FlashAttention (Metal Port)

NicoNico6/mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

NicoNico6/octopus-v4

AI for all: Build the large graph of the language models

NicoNico6/PainlessInferenceAcceleration

NicoNico6/private_llm

NicoNico6/PruneMe

NicoNico6/Pruner-Zero

Evolving Symbolic Pruning Metric from scratch

NicoNico6/QQQ

QQQ is an innovative and hardware-optimized W4A8 quantization solution.

NicoNico6/ShiftAddLLM

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

NicoNico6/SpinQuant

Code repo for the paper "SpinQuant LLM quantization with learned rotations"

NicoNico6/transformerlab-app

Experiment with Large Language Models