Wing Lian

Founder of Axolotl AI

Starred Projects (345)

miles by radixark

17.6%

327

Enterprise RL for large-scale MoE models

Starred by

Created 1 month ago

Updated 1 day ago

ROLL by alibaba

2.7%

RL library for large language models

Starred by

Created 6 months ago

Updated 1 day ago

Kimi-Linear by MoonshotAI

2.4%

Efficient linear attention architecture accelerates long-context LLMs

Created 1 month ago

Updated 1 week ago

Fast-dLLM by NVlabs

2.6%

711

Diffusion LLM inference acceleration framework

Starred by

Created 6 months ago

Updated 2 days ago

auto-round by intel

0.9%

730

Quantization algorithm for LLMs and VLMs

Starred by

Created 1 year ago

Updated 2 days ago

luminal by luminal-ai

0.3%

Deep learning library using composable compilers for high performance

Starred by

Created 2 years ago

Updated 2 weeks ago

MARS by AGI-Arena

713

Optimization framework for training large models

Created 1 year ago

Updated 1 month ago

DeepResearch by Alibaba-NLP

0.6%

17k

Benchmark for LLMs in web traversal

Starred by

Created 10 months ago

Updated 1 week ago

gemlite by dropbox

0.5%

401

Triton kernels for efficient low-bit matrix multiplication

Starred by

Created 1 year ago

Updated 1 week ago

AgentGym-RL by WooooDyy

1.6%

505

Train LLM agents for long-horizon, multi-turn decision-making

Starred by

Created 2 months ago

Updated 2 months ago

LlamaGym by KhoomeiK

0.1%

SDK for fine-tuning LLM agents with online reinforcement learning

Starred by

Created 1 year ago

Updated 1 year ago

flame by fla-org

0.6%

311

Minimal, efficient framework for LLM training

Starred by

Created 10 months ago

Updated 2 weeks ago

Soft-Thinking by eric-ai-lab

0.7%

278

Enhancing LLM reasoning via continuous concept spaces

Created 6 months ago

Updated 2 weeks ago

DFT by yongliang-wu

1.2%

502

Improving SFT generalization with reward rectification

Starred by

Created 4 months ago

Updated 3 weeks ago

dion by microsoft

1.5%

390

Orthonormal updates for faster distributed ML training

Created 6 months ago

Updated 1 week ago

mixture_of_recursions by raymin0223

1.4%

518

Adaptive LLM computation with dynamic recursion

Created 5 months ago

Updated 2 months ago

gem by axon-rl

1.4%

368

Agentic LLM training environment for interactive reinforcement learning

Starred by

Created 6 months ago

Updated 3 weeks ago

cc by kn1026

HRM by sapientinc

0.6%

12k

Hierarchical reasoning for complex tasks

Starred by

Created 4 months ago

Updated 2 months ago

RL2 by ChenmienTan

0.1%

918

Reinforcement learning for large language models

Starred by

Created 8 months ago

Updated 2 days ago

matmulfreellm by ridgerchu

0.0%

MatMul-free language models

Starred by

Created 1 year ago

Updated 4 months ago

applied-ai by meta-pytorch

0.7%

308

Applied AI experiments and examples for PyTorch

Starred by

Created 2 years ago

Updated 3 months ago

COAT by NVlabs

0.4%

250

FP8 training framework for memory efficiency

Created 1 year ago

Updated 3 months ago

SkyRL by NovaSky-AI

4.0%

RL training pipeline for multi-turn tool use LLMs, optimized for real-world tasks

scattermoe by shawntan

253

Triton-based Sparse Mixture-of-Experts for efficient deep learning

Starred by

Created 1 year ago

Updated 1 month ago

rStar by microsoft

0.4%

Research paper repo for math reasoning in small LLMs via deep thinking

Starred by

Created 1 year ago

Updated 2 months ago

Skills by NVIDIA-NeMo

1.6%

626

LLM skill-improvement pipelines for synthetic data generation, training, and evaluation

Starred by

Created 1 year ago

Updated 1 day ago

Absolute-Zero-Reasoner by LeapLabTHU

0.6%

Self-play reasoning framework needing zero data

Starred by

Created 7 months ago

Updated 3 months ago

open-webui by open-webui

0.5%

117k

Self-hosted AI platform for local LLM deployment

TTRL by PRIME-RL

1.4%

907

RL technique for unlabeled data, especially test data

Created 7 months ago

Updated 2 months ago

axolotl by axolotl-ai-cloud

0.3%

11k

CLI tool for streamlined post-training of AI models

agno by agno-agi

0.5%

36k

Lightweight library for building AI Agents with memory, knowledge, and reasoning

Starred by

Created 3 years ago

Updated 1 day ago

github-mcp-server by github

0.6%

25k

MCP server for GitHub API automation and interaction

Starred by

Created 9 months ago

Updated 2 days ago

loong by camel-ai

0.6%

466

Synthetic data generation project using LLM agents

Created 8 months ago

Updated 1 week ago

SWE-Gym by SWE-Gym

0.5%

579

Environment for training software engineering agents

Starred by

Created 1 year ago

Updated 4 months ago

GamingAgent by lmgame-org

1.6%

814

SDK for LLM/VLM gaming agents, enabling model evaluation via games

Starred by

Created 9 months ago

Updated 2 weeks ago

LLaDA by ML-GSAI

0.9%

LLM research paper exploring masked diffusion language models

Starred by

Created 9 months ago

Updated 2 weeks ago

recurrent-pretraining by seal-rg

0.2%

849

Pretraining code for depth-recurrent language model research

Starred by

Created 9 months ago

Updated 1 month ago

TransMLA by MuLabPKU

0.5%

413

Post-training method converts GQA-based LLMs to MLA models

Created 11 months ago

Updated 2 months ago

MLGym by facebookresearch

0.2%

576

Gym environment for ML research agents

Starred by

Created 9 months ago

Updated 3 months ago

coconut by facebookresearch

0.4%

Research paper implementation for LLM reasoning in latent space

Starred by

Created 10 months ago

Updated 3 months ago

native-sparse-attention-pytorch by lucidrains

0.5%

783

Sparse attention implementation from Deepseek's research paper

Created 9 months ago

Updated 3 months ago

ReasonFlux by Gen-Verse

0.2%

503

LLM post-training algorithms for data selection, RL, and inference

Created 9 months ago

Updated 2 months ago

LIMO by GAIR-NLP

0.1%

Reasoning model using less data

Starred by

Created 9 months ago

Updated 4 months ago

s1 by simplescaling

0.1%

Test-time scaling recipe for strong reasoning performance

Starred by

Created 10 months ago

Updated 5 months ago

reasoning-gym by open-thought

0.9%

Procedural dataset generator for reasoning models

Starred by

Created 10 months ago

Updated 2 weeks ago

curator by bespokelabsai

0.3%

Synthetic data curation tool for post-training and structured data extraction

Starred by

Created 1 year ago

Updated 4 months ago

RAGEN by mll-lab-nu

0.7%

Train LLM agents with reinforcement learning in interactive environments

Starred by

Created 10 months ago

Updated 2 days ago

SkyThought by NovaSky-AI

0.0%

Training recipes for Sky-T1 family of models

Starred by

Created 10 months ago

Updated 4 months ago

search-and-learn by huggingface

Recipes to scale inference-time compute of open models

Starred by

Created 11 months ago

Updated 6 months ago

buffer-of-thought-llm by YangLing0818

0.3%

671

Research paper implementation for thought-augmented LLM reasoning

Created 1 year ago

Updated 5 months ago

HuatuoGPT-o1 by FreedomIntelligence

0.3%

Medical LLM for advanced reasoning

Created 11 months ago

Updated 10 months ago

LayerSkip by facebookresearch

0.3%

347

Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding" research paper

Created 1 year ago

Updated 7 months ago

markitdown by microsoft

0.3%

83k

Python tool for converting files to Markdown for LLM text analysis

NeMo-Aligner by NVIDIA

0.2%

847

Toolkit for efficient model alignment

Starred by

Created 2 years ago

Updated 1 month ago

agency-swarm by VRSEN

0.3%

Agentic framework built on OpenAI Assistants API for automating AI workflows

Starred by

Created 2 years ago

Updated 2 days ago

instructlab by instructlab

0.1%

CLI tool for LLM alignment tuning via synthetic data

Starred by

Created 1 year ago

Updated 1 week ago

flash-linear-attention by fla-org

1.3%

Efficient Torch/Triton implementations for linear attention models

Starred by

Created 1 year ago

Updated 1 day ago

TokenFormer by Haiyang-W

579

Research paper on a fully attention-based neural network with tokenized model parameters

Created 1 year ago

Updated 9 months ago

evaluation-guidebook by huggingface

0.7%

LLM evaluation guide for practitioners

Starred by

Created 1 year ago

Updated 1 month ago

dynasaur by adobe-research

349

LLM agent framework using dynamic action creation via Python code generation

Starred by

Created 1 year ago

Updated 11 months ago

Marco-o1 by AIDC-AI

Open reasoning model for real-world problem solving

Created 1 year ago

Updated 6 months ago

SageAttention by thu-ml

1.4%

Attention kernel for plug-and-play inference acceleration

Starred by

Created 1 year ago

Updated 1 day ago

metaflow by Netflix

0.2%

10k

Framework for building and managing AI/ML systems

Muon by KellerJordan

1.2%

Optimizer for neural network hidden layers

Starred by

Created 1 year ago

Updated 1 week ago

MathBlackBox by trotsky1997

0.1%

Research paper for mathematical reasoning via LLMs

Starred by

Created 1 year ago

Updated 11 months ago

BitNet by microsoft

0.1%

24k

Inference framework for 1-bit LLMs

Starred by

Created 1 year ago

Updated 6 months ago

Aria by rhymes-ai

0.3%

Multimodal MoE model for video, document understanding, and dialog

Starred by

Created 1 year ago

Updated 10 months ago

Hands-On-Large-Language-Models by HandsOnLLM

0.6%

18k

Code examples for "Hands-On Large Language Models" book

Starred by

Created 1 year ago

Updated 4 months ago

modded-nanogpt by KellerJordan

0.8%

Language model training speedrun on 8x H100 GPUs

Starred by

Created 1 year ago

Updated 1 week ago

llama-stack by llamastack

0.2%

Composable building blocks for Llama apps

Starred by

Created 1 year ago

Updated 2 days ago

Adam-mini by zyushun

0.2%

445

PyTorch implementation of Adam-mini optimizer from a research paper

Starred by

Created 1 year ago

Updated 6 months ago

optillm by algorithmicsuperintelligence

0.9%

Optimizing inference proxy for LLMs

Starred by

Created 1 year ago

Updated 1 day ago

LLM-Blender by yuchenlin

0.1%

971

LLM ensembling framework using pairwise ranking and generative fusion

Starred by

Created 2 years ago

Updated 1 year ago

LLMs-Planning by karthikv792

0.5%

431

Benchmark for evaluating LLMs on planning tasks

Created 3 years ago

Updated 2 months ago

rStar by zhentingqi

0.2%

966

Research paper for improving small LLM reasoning via mutual reasoning

Starred by

Created 1 year ago

Updated 10 months ago

distributed-training-guide by LambdaLabsML

0.9%

543

PyTorch guide for distributed training of large language models

Starred by

Created 1 year ago

Updated 1 month ago

nyuntam by nyunAI

677

CLI tool for LLM compression via pruning, quantization, and distillation

Created 1 year ago

Updated 10 months ago

MisguidedAttention by cpldcpu

453

LLM reasoning benchmark for evaluating responses to misleading prompts

Starred by

Created 1 year ago

Updated 4 months ago

Open-Reasoning-Tasks by NousResearch

0.2%

451

Reasoning tasks collection for LLMs

Starred by

Created 1 year ago

Updated 1 year ago

long-context-attention by feifeibear

0.5%

605

Unified sequence parallel attention for long context LLM training/inference

Starred by

Created 1 year ago

Updated 1 month ago

DistillKit by arcee-ai

0.5%

785

Open-source toolkit for LLM distillation research

Starred by

Created 1 year ago

Updated 4 months ago

do-not-answer by Libr-AI

0.7%

297

Dataset for evaluating LLM safety mechanisms

Starred by

Created 2 years ago

Updated 1 year ago

fms-fsdp by foundation-model-stack

271

Efficiently train foundation models with PyTorch

Starred by

Created 1 year ago

Updated 6 days ago

OLMo by allenai

0.6%

Open language model code for training, evaluation, and inference

Starred by

Created 2 years ago

Updated 6 days ago

BAdam by Ledzy

275

Memory-efficient optimizer for large language model finetuning

Starred by

Created 1 year ago

Updated 8 months ago

snowflake-arctic by Snowflake-Labs

0.4%

557

AI research project for efficient LLM training and inference

Starred by

Created 1 year ago

Updated 1 year ago

open-instruct by allenai

1.3%

Training codebase for instruction-following language models

Starred by

Created 2 years ago

Updated 1 day ago

mdistiller by megvii-research

0.1%

877

PyTorch library for knowledge distillation research

Created 3 years ago

Updated 2 years ago

augmentoolkit by e-p-armstrong

0.4%

Data toolkit for custom LLM creation using open-source AI

Starred by

Created 2 years ago

Updated 3 weeks ago

awesome-synthetic-datasets by davanstrien

0.3%

310

Curated list of synthetic text/vision datasets and generation tools

Created 1 year ago

Updated 1 week ago

calm by zeux

625

Single-GPU inference engine for rapid LLM prototyping

Starred by

Created 2 years ago

Updated 6 months ago

MobileLLM by facebookresearch

0.1%

Sub-billion parameter LLM training code for on-device use

Starred by

Created 1 year ago

Updated 7 months ago

phoenix by Arize-ai

0.8%

AI observability platform for experimentation, evaluation, and troubleshooting

Starred by

Created 3 years ago

Updated 1 day ago

SPPO by uclaml

584

Self-Play Preference Optimization (SPPO) aligns language models via self-play

Starred by

Created 1 year ago

Updated 10 months ago

AutoIF by QwenLM

0.6%

316

Research paper for improving LLM instruction-following via self-play with execution feedback

Starred by

Created 1 year ago

Updated 1 year ago

refusal_direction by andyrdt

1.3%

304

Research paper code for analyzing refusal in language models

Starred by

Created 1 year ago

Updated 5 months ago

YaFSDP by yandex

984

Sharded data parallelism framework for transformer-like neural networks

Starred by

Created 1 year ago

Updated 3 weeks ago

chat_templates by chujiezheng

0.1%

706

Chat templates for HuggingFace LLMs

Starred by

Created 2 years ago

Updated 11 months ago

LESS by princeton-nlp

0.4%

506

Data selection research paper for targeted instruction tuning

Starred by

Created 1 year ago

Updated 1 year ago

MixEval by JinjieNi

253

Dynamic LLM evaluation suite for accurate, cost-effective benchmarking

Starred by

Created 1 year ago

Updated 1 year ago

MoRA by kongds

360

Parameter-efficient fine-tuning via high-rank updating (MoRA)

Starred by

Created 1 year ago

Updated 1 year ago

SimPO by princeton-nlp

0.2%

931

Preference optimization algorithm for LLMs (NeurIPS 2024 paper)

Starred by

Created 1 year ago

Updated 9 months ago

qodo-cover by qodo-ai

0.1%

CLI tool for AI-powered test generation and code coverage enhancement

Starred by

Created 1 year ago

Updated 5 months ago

gemma-2B-10M by mustafaaljadery

0.1%

941

Gemma 2B with 10M context length using Infini-attention

Starred by

Created 1 year ago

Updated 1 year ago

xtuner by InternLM

0.2%

LLM fine-tuning toolkit for research

Starred by

Created 2 years ago

Updated 2 days ago

GLiNER by urchade

1.2%

NER model for identifying any entity type using bidirectional transformer

Starred by

Created 2 years ago

Updated 3 days ago

contriever by facebookresearch

0.4%

764

Unsupervised dense information retrieval via contrastive learning

Starred by

Created 4 years ago

Updated 2 years ago

prometheus-eval by prometheus-eval

0.2%

LLM evaluation framework using open LLMs

Starred by

Created 1 year ago

Updated 7 months ago

LLMTest_NeedleInAHaystack by gkamradt

0.2%

LLM testing tool for evaluating in-context retrieval accuracy

Starred by

Created 2 years ago

Updated 1 year ago

selfcodealign by bigcode-project

321

Research paper for self-alignment in code generation

Starred by

Created 1 year ago

Updated 9 months ago

llm-datasets by mlabonne

0.7%

Curated datasets/tools for LLM post-training

Starred by

Created 1 year ago

Updated 2 weeks ago

rerope by bojone

384

Position embeddings research paper

Starred by

Created 2 years ago

Updated 1 year ago

LaVague by lavague-ai

0.1%

Web agent framework for automating web processes

Starred by

Created 1 year ago

Updated 10 months ago

ring-flash-attention by zhuzilin

0.2%

923

FlashAttention extension for ring attention

Starred by

Created 1 year ago

Updated 2 months ago

llamaduo by deep-diver

314

LLMOps pipeline to fine-tune small LLMs for service LLM outage prep

Starred by

Created 1 year ago

Updated 4 months ago

cohere-toolkit by cohere-ai

0.2%

RAG toolkit for LLM application development and deployment

Starred by

Created 1 year ago

Updated 1 week ago

uptrain by uptrain-ai

0.1%

Open-source platform to evaluate and improve GenAI apps

Starred by

Created 3 years ago

Updated 1 year ago

BitBLAS by microsoft

1.0%

720

Library for mixed-precision matrix multiplications, targeting quantized LLM deployment

Created 1 year ago

Updated 3 months ago

arena-hard-auto by lmarena

0.3%

963

Automatic LLM benchmark for instruction-tuned models, correlating with human preference

Starred by

Created 2 years ago

Updated 5 months ago

ChunkLlama by HKUNLP

0.5%

443

Training-free method for extending LLM context windows

Created 1 year ago

Updated 1 year ago

dstack by dstackai

0.5%

Open-source tool for simplifying GPU allocation and AI workload orchestration

Starred by

Created 3 years ago

Updated 2 days ago

rho by microsoft

0.2%

447

LLM pretraining research paper using selective language modeling (SLM)

Starred by

Created 1 year ago

Updated 1 year ago

dify by langgenius

0.5%

120k

Open-source LLM app development platform

attorch by BobMcDear

584

PyTorch nn module subset, implemented in Python using Triton

Starred by

Created 2 years ago

Updated 3 months ago

mixtral-offloading by dvmazur

Inference optimization for Mixtral-8x7B models

Starred by

Created 1 year ago

Updated 1 year ago

auto-code-rover by AutoCodeRoverSG

0.1%

Autonomous software engineer for program improvement

Starred by

Created 1 year ago

Updated 7 months ago

BitNet-Transformers by Beomi

310

HuggingFace Transformers implementation of BitNet scaling for LLMs

Created 2 years ago

Updated 1 year ago

EasyContext by jzhang38

750

Recipes for language model context length extrapolation to 1M tokens

Starred by

Created 1 year ago

Updated 1 year ago

pyreft by stanfordnlp

0.2%

Python library for representation finetuning (ReFT) of language models

Starred by

Created 1 year ago

Updated 9 months ago

hlb-gpt by tysam-code

352

Researcher's toolbench for GPT model exploration

Starred by

Created 2 years ago

Updated 1 year ago

aideml by WecoAI

0.1%

ML engineering agent for automated AI R&D, surpassing human experts

Starred by

Created 1 year ago

Updated 3 weeks ago

BitNet by kyegomez

0.1%

PyTorch implementation of BitNet research paper

Starred by

Created 2 years ago

Updated 1 month ago

horovod by horovod

0.1%

15k

Distributed training framework for TF, Keras, PyTorch, and MXNet

Starred by

+19

Created 8 years ago

Updated 4 weeks ago

dataverse by UpstageAI

565

ETL pipeline for LLM data processing

Starred by

Created 2 years ago

Updated 1 year ago

hqq by dropbox

0.1%

894

Model quantizer for fast, accurate post-training quantization, skipping calibration

Starred by

Created 2 years ago

Updated 1 month ago

Triton-Puzzles by srush

0.6%

Interactive puzzles for learning Triton

Starred by

Created 1 year ago

Updated 1 year ago

repeng by vgel

0.3%

663

Python library for representation engineering control vectors

Starred by

Created 1 year ago

Updated 2 months ago

cobra by h-zhao1997

289

Multimodal LLM research paper extending Mamba for efficient inference

Created 1 year ago

Updated 10 months ago

hackathon by mistralai-sf24

446

Minimal code for running and finetuning a 7B transformer model

Starred by

Created 1 year ago

Updated 1 year ago

raft by rapidsai

0.1%

955

CUDA-accelerated primitives for ML/data mining algorithms

Starred by

Created 6 years ago

Updated 5 days ago

maestro by Doriandarko

0.1%

Framework for Claude Opus to orchestrate subagents

Starred by

Created 1 year ago

Updated 1 year ago

quiet-star by ezelikman

0.3%

742

Research code for self-teaching language models

Starred by

Created 1 year ago

Updated 1 year ago

ml-engineering by stas00

0.4%

16k

Open book for LLM/VLM training engineers

Starred by

+17

Created 5 years ago

Updated 1 week ago

chatbot-ui by mckaywrigley

0.1%

33k

Open-source AI chat app

orpo by xfactlab

0.2%

467

Preference optimization without a reference model

Starred by

Created 1 year ago

Updated 1 year ago

SWE-bench by SWE-bench

0.8%

Benchmark for evaluating LLMs on real-world GitHub issues

OpenHands by OpenHands

0.2%

65k

AI platform for software development agents

FastV by pkunlp-icler

0.4%

521

Inference acceleration for large vision-language models (research paper)

Created 1 year ago

Updated 11 months ago

airllm by lyogavin

0.3%

Inference optimization for LLMs on low-resource hardware

Starred by

Created 2 years ago

Updated 2 months ago

daytona by daytonaio

3.4%

35k

Infrastructure for running AI-generated code

Starred by

Created 1 year ago

Updated 2 days ago

VisionLLaMA by Meituan-AutoML

390

Vision transformer research paper

Created 1 year ago

Updated 1 year ago

fsdp_qlora by AnswerDotAI

0.2%

Training script for LLMs using QLoRA + FSDP

Starred by

Created 1 year ago

Updated 1 year ago

h2o-llmstudio by h2oai

0.4%

LLM Studio: framework for LLM fine-tuning via GUI or CLI

Starred by

Created 2 years ago

Updated 2 months ago

ChatMusician by hf-lin

0.3%

285

LLM for music understanding and generation

Created 2 years ago

Updated 1 year ago

AnyGPT by OpenMOSS

0.2%

862

Multimodal LLM research paper for any-to-any modality conversion

Starred by

Created 1 year ago

Updated 1 year ago

FlagEmbedding by FlagOpen

0.4%

11k

Toolkit for retrieval and RAG applications

Starred by

Created 2 years ago

Updated 1 month ago

self-rewarding-lm-pytorch by lucidrains

0.1%

Training framework for self-rewarding language models

Starred by

Created 1 year ago

Updated 1 year ago

crewAI by crewAIInc

0.5%

41k

Framework for autonomous AI agent orchestration via role-playing and collaboration

resource-stream by gpu-mode

0.3%

CUDA resource collection for GPU programming

Starred by

Created 1 year ago

Updated 2 months ago

metal-flash-attention by philipturner

557

Metal port of FlashAttention for Apple silicon

Starred by

Created 2 years ago

Updated 1 year ago

LLMs-from-scratch by rasbt

0.9%

80k

Educational resource for LLM construction in PyTorch

mlx-examples by ml-explore

0.2%

Examples using the MLX framework

Starred by

Created 2 years ago

Updated 1 week ago

ai-codereviewer by villesau

0.6%

982

GitHub Action for AI-powered code review

Starred by

Created 2 years ago

Updated 1 year ago

deita by hkust-nlp

576

Data-efficient instruction tuning for LLM alignment (ICLR 2024)

Starred by

Created 2 years ago

Updated 11 months ago

AutoAWQ by casper-hansen

0.3%

AutoAWQ is a tool for 4-bit quantized LLM inference

Starred by

Created 2 years ago

Updated 6 months ago

ProxyAI by carlrobertoh

0.2%

JetBrains IDE copilot for coding assistance

Starred by

Created 2 years ago

Updated 1 week ago

EAGLE by SafeAILab

0.9%

Speculative decoding research paper for faster LLM inference

Starred by

Created 2 years ago

Updated 1 week ago

HALOs by ContextualAI

0.1%

894

Library for aligning LLMs using human-aware loss functions

Starred by

Created 2 years ago

Updated 2 months ago

mamba by state-spaces

0.4%

17k

Mamba SSM architecture for sequence modeling

modelz-llm by tensorchord

275

Inference server for open-source LLMs, offering an OpenAI-compatible API

Created 2 years ago

Updated 2 years ago

unsloth by unslothai

0.5%

49k

Finetuning tool for LLMs, targeting speed and memory efficiency

gpt-researcher by assafelovic

0.3%

24k

Autonomous agent for web/local research, generating cited reports

Starred by

Created 2 years ago

Updated 2 weeks ago

functionary by MeetKai

Chat language model for tool use and result interpretation

Starred by

Created 2 years ago

Updated 2 weeks ago

Logic-LLM by teacherpeterpan

0.3%

364

Logic-LM: Framework for improved logical reasoning via LLMs and symbolic solvers

Created 2 years ago

Updated 1 year ago

LLMSurvey by RUCAIBox

0.1%

12k

Survey paper for large language models

Starred by

Created 2 years ago

Updated 8 months ago

distilabel by argilla-io

0.6%

Framework for synthetic data and AI feedback pipelines

long-llms-learning by Strivin0311

269

Literature repository for long-context LLM methodologies

Starred by

Created 2 years ago

Updated 1 year ago

MergeLM by yule-BUAA

0.1%

860

Codebase for merging language models via parameter averaging

Starred by

Created 2 years ago

Updated 1 year ago

Video-LLaVA by PKU-YuanGroup

0.1%

Video-LLaVA: Multimodal model for video/image understanding via LLM

Starred by

Created 2 years ago

Updated 1 year ago

medAlpaca by kbressem

543

LLM finetuned for medical question answering

Starred by

Created 2 years ago

Updated 2 years ago

intel-extension-for-transformers by intel

Transformer toolkit for GenAI/LLM acceleration on Intel platforms

Starred by

Created 3 years ago

Updated 1 year ago

representation-engineering by andyzoujm

0.2%

917

AI transparency via representation engineering

Starred by

Created 2 years ago

Updated 1 year ago

multimodal by facebookresearch

0.1%

PyTorch library for multimodal multi-task model training

Starred by

Created 3 years ago

Updated 6 days ago

S-LoRA by S-LoRA

0.3%

System for scalable LoRA adapter serving

Starred by

Created 2 years ago

Updated 1 year ago

DeepSpeed by deepspeedai

0.2%

41k

Deep learning optimization library for distributed training and inference

continue by continuedev

0.4%

30k

IDE extension for custom AI code assistants

llama-cookbook by meta-llama

0.1%

18k

Guide for building with Llama models

finetuner by jina-ai

0.1%

Cloud tool for task-oriented embedding finetuning of models like BERT and CLIP

Starred by

Created 4 years ago

Updated 1 year ago

ludwig by ludwig-ai

0.0%

12k

Low-code framework for custom AI models (LLMs, neural networks)

img2dataset by rom1504

0.2%

CLI tool for creating large image datasets from URLs

distilling-step-by-step by google-research

0.2%

565

Code for research paper on knowledge distillation

Starred by

Created 2 years ago

Updated 2 years ago

Cherry_LLM by tianyi-lab

1.2%

407

Research paper for LLM instruction tuning via self-guided data selection

Created 2 years ago

Updated 5 months ago

Reflection_Tuning by tianyi-lab

0.3%

365

Research paper for LLM instruction tuning via data recycling

Starred by

Created 2 years ago

Updated 1 year ago

instructor by 567-labs

0.3%

12k

SDK for structured LLM outputs using Pydantic models

YiVal by YiVal

Prompt engineering assistant for GenAI apps

Starred by

Created 2 years ago

Updated 1 year ago

LLM-Shearing by princeton-nlp

632

Code for LLM pre-training acceleration via structured pruning (ICLR 2024)

Starred by

Created 2 years ago

Updated 1 year ago

letta by letta-ai

0.4%

19k

Agent framework for stateful agents with memory, reasoning, and context management

Starred by

+17

Created 2 years ago

Updated 2 days ago

CogVLM by zai-org

0.1%

VLM for image understanding and multi-turn dialogue

Starred by

Created 2 years ago

Updated 1 year ago

ragas by vibrantlabsai

0.7%

12k

Toolkit for LLM application evaluation

NEFTune by neelsjain

0.3%

405

Technique to improve instruction finetuning of LLMs

Starred by

Created 2 years ago

Updated 1 year ago

FireAct by anchen1011

286

Language agent fine-tuning research paper

Starred by

Created 2 years ago

Updated 2 years ago

LLaVA by haotian-liu

0.3%

24k

Multimodal assistant with GPT-4 level capabilities

alignment-handbook by huggingface

0.1%

Handbook for aligning language models with human/AI preferences

autolabel by refuel-ai

0.1%

Python library to label text datasets using LLMs

Starred by

Created 2 years ago

Updated 9 months ago

EmpatheticDialogues by facebookresearch

531

PyTorch code for empathetic dialogue research

Starred by

Created 6 years ago

Updated 4 years ago

world-models by wesg52

257

Research paper code for extracting spatial/temporal world models from LLMs

Starred by

Created 2 years ago

Updated 2 years ago

OpenGPT by CogStack

361

Framework for grounded instruction datasets and domain-expert LLMs

Starred by

Created 2 years ago

Updated 2 years ago

Medusa by FasterDecoding

0.1%

Framework for accelerating LLM generation using multiple decoding heads

Starred by

Created 2 years ago

Updated 1 year ago

open_flamingo by mlfoundations

0.1%

Open-source framework for training large multimodal models

Starred by

Created 3 years ago

Updated 1 year ago

textbook_quality by VikParuchuri

507

Synthetic data generator for LLM pretraining

Starred by

Created 2 years ago

Updated 2 years ago

tree-of-thought-llm by princeton-nlp

0.2%

Research paper implementation for Tree of Thoughts (ToT) prompting

Starred by

Created 2 years ago

Updated 10 months ago

LongLoRA by dvlab-research

0.0%

LongLoRA: Efficient fine-tuning for long-context LLMs

Starred by

Created 2 years ago

Updated 1 year ago

kani by zhudotexe

594

Microframework for chat-based language models with tool use/function calling

Starred by

Created 2 years ago

Updated 2 weeks ago

DoLa by voidism

524

Decoding strategy research paper for improving factuality in LLMs

Starred by

Created 2 years ago

Updated 10 months ago

varuna by microsoft

252

Tool for efficient large DNN model training on commodity hardware

Starred by

Created 4 years ago

Updated 1 year ago

BLoRA by sabetAI

347

Inference optimization for batched LoRA adapters

Starred by

Created 2 years ago

Updated 2 years ago

TinyLlama by jzhang38

0.1%

Tiny pretraining project for a 1.1B Llama model

sparsegpt by IST-DASLab

851

Code for massive language model one-shot pruning (ICML 2023 paper)

Starred by

Created 2 years ago

Updated 1 year ago

LLM-Pruner by horseee

LLM structural pruner for model compression

Created 2 years ago

Updated 1 year ago

graph-of-thoughts by spcl

0.2%

Graph-of-Thoughts: LLM framework for complex problem-solving

Starred by

Created 2 years ago

Updated 11 months ago

tensor_parallel by BlackSamorez

658

PyTorch module for multi-GPU model parallelism

Starred by

Created 3 years ago

Updated 1 year ago

relora by Guitaricet

469

PEFT pretraining code for ReLoRA research paper

Starred by

Created 2 years ago

Updated 1 year ago

wandbot by wandb

310

Support bot for Weights & Biases' AI tools, running in Discord, Slack, ChatGPT, and Zendesk

Starred by

Created 2 years ago

Updated 1 month ago

LightLLM by ModelTC

0.5%

Python framework for LLM inference and serving

Starred by

Created 2 years ago

Updated 2 days ago

lmdeploy by InternLM

0.5%

Toolkit for LLM compression, deployment, and serving

Starred by

Created 2 years ago

Updated 1 day ago

llama-chat by replicate

836

Next.js app for Llama 3 chat UI development

Created 2 years ago

Updated 1 year ago

llama2-chatbot by a16z-infra

Streamlit chatbot app for interacting with LLMs

Starred by

Created 2 years ago

Updated 2 years ago

IncognitoPilot by silvanmelchior

442

AI code interpreter for local data processing, like ChatGPT Code Interpreter

Created 2 years ago

Updated 2 years ago

ai-town by a16z-infra

0.2%

AI town starter kit for building a virtual world

octopack by bigcode-project

474

Code LLM instruction tuning research paper

Starred by

Created 2 years ago

Updated 9 months ago

outlines by dottxt-ai

0.6%

13k

SDK for structured LLM text generation

bubogpt by magic-research

510

Multi-modal LLM for joint text, vision, and audio understanding

Created 2 years ago

Updated 2 years ago

MetaGPT by FoundationAgents

0.2%

60k

Multi-agent framework for collaborative AI software development

Starred by

Created 2 years ago

Updated 1 month ago

pykoi-rlhf-finetuned-transformers by CambioML

0.2%

412

Python library for reinforcement learning with human feedback (RLHF)

Starred by

Created 2 years ago

Updated 2 months ago

ChainFury by NimbleBoxAI

450

Open-source chaining engine for production AI apps

Starred by

Created 2 years ago

Updated 1 year ago

candle by huggingface

0.4%

19k

Minimalist ML framework for Rust, emphasizing performance and ease of use

Megatron-LLM by epfLLM

584

Distributed trainer for LLMs

Starred by

Created 2 years ago

Updated 1 year ago

ToolBench by OpenBMB

0.2%

Open platform for LLM tool learning (ICLR'24 spotlight)

Starred by

Created 2 years ago

Updated 6 months ago

gpt-engineer by AntonOsika

0.1%

55k

CLI platform for code generation experimentation

RRHF by GanjinZero

811

RRHF for aligning LLMs to human preferences

Starred by

Created 2 years ago

Updated 2 years ago

LLaMA-Factory by hiyouga

0.6%

63k

Unified fine-tuning tool for 100+ LLMs & VLMs (ACL 2024)

exllama by turboderp

0.0%

Llama implementation for memory-efficient quantized weights

Starred by

Created 2 years ago

Updated 2 years ago

doremi by sangmichaelxie

347

PyTorch for optimizing data mixtures in language model datasets

Starred by

Created 2 years ago

Updated 1 year ago

UltraChat by thunlp

0.1%

Multi-round dialogue dataset and models for chat language model training

Starred by

Created 2 years ago

Updated 1 year ago

RealChar by Shaunwei

0.0%

Real-time AI character/companion creation and interaction codebase

Starred by

Created 2 years ago

Updated 1 year ago

serve by jina-ai

0.0%

22k

Framework for building cloud-native multimodal AI apps

aider by Aider-AI

0.4%

39k

AI pair programming in your terminal

LMFlow by OptimalScale

0.0%

Toolkit for finetuning and inference of large foundation models

Starred by

Created 2 years ago

Updated 2 days ago

baize-chatbot by project-baize

Chat model trained via LoRA, using ChatGPT-generated dialogs

Starred by

Created 2 years ago

Updated 1 year ago

ToolQA by night-chen

282

Dataset for evaluating LLMs using external tools

Created 2 years ago

Updated 2 years ago

SuperAGI by TransformerOptimus

0.1%

17k

Open-source framework for autonomous AI agent development

Starred by

Created 2 years ago

Updated 10 months ago

audiocraft by facebookresearch

0.1%

23k

PyTorch library for audio processing and generation research

guidance by guidance-ai

0.1%

21k

Guidance is a programming paradigm for steering LLMs

open_llama by openlm-research

0.0%

Open-source reproduction of LLaMA models

RL4LMs by allenai

0.1%

RL library to fine-tune language models to human preferences

Starred by

Created 3 years ago

Updated 1 year ago

SwiftSage by SwiftSage

0.6%

319

Agent system for reasoning with LLMs via in-context reinforcement learning

Created 2 years ago

Updated 1 year ago

ctransformers by marella

0.1%

Python bindings for fast Transformer model inference

Starred by

Created 2 years ago

Updated 1 year ago

developer by smol-ai

0.0%

12k

Agent for embedding a developer in your app

MeZO by princeton-nlp

0.1%

Research paper implementation for memory-efficient LM fine-tuning

Starred by

Created 2 years ago

Updated 1 year ago

ImageBind by facebookresearch

0.1%

PyTorch implementation for multimodal embeddings research paper

Starred by

Created 2 years ago

Updated 1 week ago

xtreme1 by xtreme1-io

2.5%

Open-source platform for multimodal training data annotation

Starred by

Created 3 years ago

Updated 4 months ago

sudolang by paralleldrive

1.1%

VS Code extension for LLM-based programming with SudoLang

Starred by

Created 2 years ago

Updated 2 days ago

poe-api by ading2210

0.0%

Python API for Quora's Poe (unmaintained)

Created 2 years ago

Updated 2 years ago

Local-LLM-Comparison-Colab-UI by Troyanovsky

Local LLM comparison via Colab WebUI links

Starred by

Created 2 years ago

Updated 6 days ago

airoboros by jondurbin

Self-instruct tool for LLM finetuning

Starred by

Created 2 years ago

Updated 1 year ago

PaLM by conceptofmind

818

Open-source PaLM implementation for language model research

Starred by

Created 2 years ago

Updated 1 year ago

TruthfulQA by sylinrl

0.5%

847

Benchmark dataset for evaluating truthfulness of language models

Starred by

Created 4 years ago

Updated 10 months ago

private-gpt by zylon-ai

0.1%

57k

Private AI API for local document interaction using LLMs

PMC-LLaMA by chaoyi-wu

0.1%

672

Medical LLM for instruction-following in the medical domain

Created 2 years ago

Updated 1 year ago

openlm by r2d4

373

OpenAI-compatible Python client for calling LLMs

Starred by

Created 2 years ago

Updated 2 years ago

FasterTransformer by NVIDIA

0.1%

Optimized transformer library for inference

unlimiformer by abertsch72

Research paper for long-range transformers with unlimited input

Starred by

Created 2 years ago

Updated 1 year ago

gpt-neox by EleutherAI

0.1%

Framework for training large-scale autoregressive language models

toolformer by conceptofmind

0.3%

379

Open-source implementation of Toolformer research paper

Starred by

Created 2 years ago

Updated 2 years ago

bark by suno-ai

0.1%

39k

Generative audio model for realistic speech and sound effects

chat-langchain by langchain-ai

0.2%

Chatbot for question answering over LangChain documentation

Starred by

Created 2 years ago

Updated 6 days ago

LaMini-LM by mbzuai-nlp

824

Small, efficient language models distilled from ChatGPT for research

Starred by

Created 2 years ago

Updated 2 years ago

ChatRWKV by BlinkDL

10k

Open-source chatbot powered by the RWKV RNN language model

Starred by

Created 2 years ago

Updated 2 months ago

RWKV-LM by BlinkDL

0.1%

14k

RNN for LLM, transformer-level performance, parallelizable training

LocalAI by mudler

1.0%

39k

Open-source OpenAI alternative for local AI inference

WizardLM by nlpxucan

0.1%

LLMs built using Evol-Instruct for complex instruction following

chameleon-llm by lupantech

Research paper code for plug-and-play compositional reasoning with LLMs

Starred by

Created 2 years ago

Updated 1 year ago

llama-lab by run-llama

0.1%

LlamaIndex projects for LLM data augmentation

Starred by

Created 2 years ago

Updated 2 years ago

EdgeGPT by acheong08

Reverse-engineered API for Microsoft Bing Chat (archived)

Starred by

Created 2 years ago

Updated 2 years ago

gisting by jayelm

0.3%

300

Research paper implementation for prompt compression via learned "gist" tokens

Starred by

Created 2 years ago

Updated 9 months ago

gpt-llama.cpp by keldenl

597

API wrapper for local LLM inference, emulating OpenAI's GPT endpoints

Starred by

Created 2 years ago

Updated 2 years ago

memit by kmeng01

0.2%

533

Transformer memory mass-editor (ICLR 2023 research paper)

Starred by

Created 3 years ago

Updated 1 year ago

dl4math by lupantech

370

DL4MATH: Deep learning resources for mathematical reasoning

Created 3 years ago

Updated 1 year ago

MiniGPT-4 by Vision-CAIR

0.0%

26k

Vision-language model for multi-task learning

auto-cot by amazon-science

0.1%

Research paper implementation for automatic chain-of-thought prompting

Starred by

Created 3 years ago

Updated 1 year ago

OpenChatKit by togethercomputer

0.0%

Open-source toolkit for building specialized/general-purpose chat models

PythonProgrammingPuzzles by microsoft

993

Python puzzle dataset for AI programming proficiency research

Created 4 years ago

Updated 1 year ago

RedPajama-Data by togethercomputer

0.1%

Dataset pipeline for training large language models

Starred by

Created 2 years ago

Updated 11 months ago

unstructured by Unstructured-IO

0.4%

13k

ETL solution for structuring unstructured data for language models

whisper by openai

0.3%

91k

Speech recognition model for multilingual transcription/translation

LLaMA_MPS by jankais3r

586

LLM inference on Apple Silicon GPUs

Starred by

Created 2 years ago

Updated 2 years ago

dolly by databrickslabs

11k

Instruction-following LLM trained on the Databricks Machine Learning Platform

minimal-llama by zphang

457

Code for running and fine-tuning LLaMA models

Starred by

Created 2 years ago

Updated 2 years ago

zero_shot_cot by kojima-takeshi188

434

Reasoning framework for LLMs, based on a NeurIPS 2022 paper

Starred by

Created 3 years ago

Updated 2 years ago

safari by HazyResearch

0.1%

904

Research paper implementations for sequence modeling with convolutions

Starred by

Created 2 years ago

Updated 1 year ago

EasyLM by young-geng

0.0%

LLM training/finetuning framework in JAX/Flax

Starred by

Created 3 years ago

Updated 1 year ago

AlpacaDataCleaned by gururise

0.1%

Cleaned dataset for Alpaca LLM training

Starred by

Created 2 years ago

Updated 2 years ago

trl by huggingface

0.6%

16k

Library for transformer RL

ThoughtSource by OpenBioLink

0.1%

Framework for chain-of-thought reasoning data and tools

Starred by

Created 3 years ago

Updated 11 months ago

GPT-4-LLM by Instruction-Tuning-with-GPT-4

0.0%

GPT-4 data for instruction-tuning LLMs via supervised/RL

Starred by

Created 2 years ago

Updated 2 years ago

lit-llama by Lightning-AI

0.1%

LLaMA implementation for pretraining, finetuning, and inference

Starred by

Created 2 years ago

Updated 5 months ago

AutoGPT by Significant-Gravitas

0.1%

180k

AI agent platform for building, deploying, and running autonomous workflows

LLaMA-Adapter by OpenGVLab

0.1%

Efficient fine-tuning for instruction-following LLaMA models

Starred by

Created 2 years ago

Updated 1 year ago

pygpt4all by nomic-ai

Python bindings for local LLM inference (deprecated)

Starred by

Created 2 years ago

Updated 2 years ago

chatllama by henrywoo

Open-source implementation for LLaMA-based ChatGPT, runnable on a single GPU

Created 2 years ago

Updated 10 months ago

optimate by nebuly-ai

Collection of libraries to optimize AI model performances

Starred by

Created 3 years ago

Updated 1 year ago

GPTeacher by teknium1

GPT-4 generated datasets for instruction tuning

Starred by

Created 2 years ago

Updated 2 years ago

chatgpt-universe by cedrickchee

379

Collection of ChatGPT, GPT, and LLM resources

Created 3 years ago

Updated 1 year ago

langchain by langchain-ai

0.4%

121k

Framework for building LLM-powered applications

xTuring by stochasticai

SDK for fine-tuning and customizing open-source LLMs

Starred by

Created 2 years ago

Updated 4 days ago

ai-pdf-chatbot-langchain by mayooear

0.1%

16k

AI chatbot agent for PDF document Q&A using LangChain & LangGraph

Starred by

Created 2 years ago

Updated 9 months ago

natbot by nat

Browser automation via GPT-3

Starred by

Created 3 years ago

Updated 1 year ago

ReAct by ysymyth

0.5%

GPT-3 prompting code for ReAct research paper

Starred by

Created 3 years ago

Updated 1 year ago

ChatGLM-finetune-LoRA by lich99

722

LoRA finetuning code for ChatGLM-6b

Starred by

Created 2 years ago

Updated 2 years ago

Llama-X by AetherCortex

Open academic research project improving LLaMA to SOTA LLM

Starred by

Created 2 years ago

Updated 2 years ago

flash-attention by Dao-AILab

0.6%

21k

Fast, memory-efficient attention implementation

FastChat by lm-sys

0.1%

39k

Open platform for training, serving, and evaluating LLM-based chatbots

text-generation-inference by huggingface

0.2%

11k

Rust/Python/gRPC server for fast LLM text generation

ChatDoctor by Kent0n-Li

Medical chat model fine-tuned on LLaMA for medical domain Q&A

Starred by

Created 2 years ago

Updated 1 year ago

gpt4all by nomic-ai

0.0%

77k

Desktop app for local LLM inference, no GPU/API needed

toolformer-pytorch by lucidrains

Pytorch implementation of Toolformer for language models using external tools

Starred by

Created 2 years ago

Updated 1 year ago

text-generation-webui by oobabooga

0.1%

46k

Web UI for LLM text generation

gptq by IST-DASLab

0.1%

Code for GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers

Starred by

Created 3 years ago

Updated 1 year ago

PaLM-rlhf-pytorch by lucidrains

0.1%

RLHF implementation on PaLM

Starred by

Created 3 years ago

Updated 1 month ago

trlx by CarperAI

Distributed RLHF for LLMs

alpaca_lora_4bit by johnsmith0031

535

Fine-tuning and inference tool for quantized LLaMA models

Starred by

Created 2 years ago

Updated 2 years ago

chatgpt-retrieval-plugin by openai

0.0%

21k

Retrieval plugin for custom GPTs, function calling, or assistants APIs

GPTQ-for-LLaMa by qwopqwop200

0.0%

4-bit quantization for LLaMA models using GPTQ

Starred by

Created 2 years ago

Updated 1 year ago

dalai by cocktailpeanut

0.0%

13k

Local LLM inference via CLI tool and Node.js API

Starred by

Created 2 years ago

Updated 1 year ago

alpaca-lora by tloen

0.0%

19k

LoRA fine-tuning for LLaMA

stanford_alpaca by tatsu-lab

0.1%

30k

Instruction-following LLaMA model training and data generation

ColossalAI by hpcaitech

0.1%

41k

AI system for large-scale parallel training

agentic by transitive-bullshit

0.0%

18k

AI agent stdlib for LLM-based TypeScript tooling

Starred by

Created 3 years ago

Updated 1 month ago

dagger by dagger

0.2%

15k

Open-source runtime for composable workflows, ideal for AI agents

Starred by

Created 6 years ago

Updated 4 days ago

sdk-python by temporalio

1.0%

878

Python SDK for Temporal, a distributed orchestration engine

Starred by

Created 3 years ago

Updated 5 days ago

docker-lambda by lambci

Deprecated: Docker images for replicating the AWS Lambda environment locally

Starred by

Created 9 years ago

Updated 2 years ago

kong by Kong

0.1%

42k

Cloud-native API and AI gateway for microservice orchestration

awesome-machine-learning by josephmisiti

0.2%

71k

Curated list of ML frameworks, libraries, and software

hackathon-starter by sahat

0.0%

35k

Node.js boilerplate for web applications

Feedback? Help us improve.