Pawel Garbacki

Cofounder of Fireworks AI

Starred Projects (380)

awesome-ai-leaderboard by SAILResearch

372

Curated list of foundation model leaderboards

Created 2 years ago

Updated 7 hours ago

tokenspeed by lightseekorg

0.2%

Speed-of-light LLM inference engine

Starred by

Created 2 months ago

Updated 5 hours ago

RouteLLM by lm-sys

Framework for LLM routing and cost reduction (research paper)

Starred by

Created 2 years ago

Updated 1 year ago

next-evals-oss by vercel

300

AI agentic framework for Next.js coding evaluations

Starred by

Created 9 months ago

Updated 1 week ago

router by workweave

865

LLM model routing proxy for agentic systems

Starred by

Created 3 months ago

Updated 12 hours ago

Qwen-AgentWorld by QwenLM

0.1%

860

Language world models for general agents

Created 1 month ago

Updated 1 week ago

semantic-router by vllm-project

Intelligent LLM routing for efficient inference

Starred by

Created 11 months ago

Updated 1 day ago

harbor by harbor-framework

0.4%

Harness for AI agent evaluation and RL optimization

Starred by

+12

Created 11 months ago

Updated 11 hours ago

andrej-karpathy-skills by multica-ai

0.0%

195k

LLM code generation guidelines for enhanced reliability

Starred by

Created 6 months ago

Updated 3 months ago

ntkmirror by leochlon

347

LoRA-free fine-tuning for causal language models

Created 2 months ago

Updated 1 month ago

claude-code-router by musistudio

0.0%

36k

Router for Claude Code requests

Starred by

Created 1 year ago

Updated 11 hours ago

litellm by BerriAI

0.0%

54k

SDK/proxy for calling 100+ LLM APIs using the OpenAI format

Starred by

+29

Created 3 years ago

Updated 10 hours ago

claude-code by yasasbanukaofficial

AI agent CLI for developers with advanced capabilities

Created 3 months ago

Updated 3 months ago

smfs by supermemoryai

0.2%

468

Agent memory as a mountable, searchable filesystem

Created 3 months ago

Updated 1 month ago

Nemotron by NVIDIA-NeMo

0.1%

Open models for advanced AI workflows

Created 9 months ago

Updated 6 days ago

nanochat by karpathy

0.0%

57k

A minimal, full-stack LLM implementation for accessible AI development

harvey-labs by harveyai

0.2%

541

Benchmark for evaluating LLM agents in legal domains

Starred by

Created 3 months ago

Updated 6 hours ago

AgentBench by THUDM

Benchmark for evaluating LLMs as agents across diverse environments

Starred by

Created 3 years ago

Updated 5 months ago

OpenClaw-RL by Gen-Verse

Personalize AI agents through conversational reinforcement learning

Starred by

Created 5 months ago

Updated 2 months ago

ml-intern by huggingface

0.0%

11k

AI engineer for autonomous ML research, training, and deployment

Starred by

Created 9 months ago

Updated 1 week ago

EverOS by EverMind-AI

0.0%

11k

Enterprise-grade AI memory system for persistent understanding

Starred by

Created 9 months ago

Updated 5 hours ago

qmd by tobi

28k

AI-powered local search for your documents

aiconfigurator by ai-dynamo

369

LLM serving configuration optimization

Starred by

Created 1 year ago

Updated 16 hours ago

reasoning-gym by open-thought

Procedural dataset generator for reasoning models

Starred by

Created 1 year ago

Updated 3 months ago

pi by earendil-works

0.1%

75k

AI agent framework and LLM deployment tools

Starred by

+31

Created 11 months ago

Updated 1 day ago

claw-code by ultraworkers

0.0%

195k

Agent harness engineering framework

Starred by

Created 3 months ago

Updated 1 month ago

OpenResearcher by TIGER-AI-Lab

Agentic LLM for long-horizon deep research trajectory synthesis

Starred by

Created 5 months ago

Updated 1 month ago

autokernel by RightNow-AI

0.1%

Autonomous GPU kernel optimization for PyTorch

Starred by

Created 4 months ago

Updated 4 months ago

gstack by garrytan

0.0%

123k

Specialized AI coding assistant framework

mle-bench by openai

Benchmark for evaluating AI agents on machine learning engineering tasks

Starred by

Created 1 year ago

Updated 3 months ago

mem9 by mem9-ai

Persistent cloud memory for AI agents

Starred by

Created 4 months ago

Updated 4 days ago

cutlass by NVIDIA

0.0%

10k

CUDA C++ and Python DSLs for high-performance linear algebra

autoresearch by karpathy

92k

Autonomous LLM research agent for single-GPU training

Starred by

+23

Created 4 months ago

Updated 4 months ago

doc-to-lora by SakanaAI

781

Instantly internalize factual context into LLMs using hypernetworks

Starred by

Created 5 months ago

Updated 1 month ago

ralph by snarktank

0.0%

21k

Autonomous AI agent loop for iterative task completion

Starred by

Created 6 months ago

Updated 5 months ago

paperbanana by llmsresearch

Agentic framework for automated academic illustration

Starred by

Created 5 months ago

Updated 1 month ago

agent-lightning by microsoft

17k

Train any AI agent with rollouts and feedback

Starred by

Created 1 year ago

Updated 1 week ago

PaperBanana by dwzhu-pku

0.0%

Automating academic illustration generation for AI scientists

Created 5 months ago

Updated 1 month ago

openclaw by openclaw

384k

WhatsApp automation and AI integration for machine actions

Starred by

+42

Created 8 months ago

Updated 4 hours ago

opro by google-deepmind

767

Research paper code for LLMs as optimizers

Starred by

Created 2 years ago

Updated 1 year ago

Engram by deepseek-ai

Scalable conditional memory for large language models

Starred by

Created 6 months ago

Updated 6 months ago

agent-client-protocol by agentclientprotocol

0.2%

Standardizes AI agent-editor communication for code modification

Starred by

Created 1 year ago

Updated 6 hours ago

claude-agent-acp by agentclientprotocol

Claude Code integration for ACP clients

Starred by

Created 11 months ago

Updated 1 day ago

ag-ui by ag-ui-protocol

0.0%

15k

Protocol for agent-user interaction in frontends

Starred by

Created 1 year ago

Updated 21 hours ago

toad by batrachianai

0.0%

Unified AI interface for terminal agents

Starred by

Created 1 year ago

Updated 2 months ago

dflash by z-lab

0.1%

Ultra-fast speculative decoding for LLMs

Starred by

Created 6 months ago

Updated 2 months ago

kilocode by Kilo-Org

0.1%

26k

VS Code AI agent for coding tasks

Starred by

Created 1 year ago

Updated 4 hours ago

vibetunnel by amantus-ai

Turn any browser into your terminal

Starred by

Created 1 year ago

Updated 2 weeks ago

agentskills by agentskills

0.0%

23k

Standardized skills for AI agents

Starred by

Created 7 months ago

Updated 2 weeks ago

OpenTinker by open-tinker

676

RL-as-a-Service infrastructure for foundation models

Starred by

Created 7 months ago

Updated 4 months ago

nmoe by Noumena-Network

394

High-performance MoE trainer for NVIDIA B200 GPUs

Starred by

Created 7 months ago

Updated 4 months ago

sonic-moe by Dao-AILab

732

Accelerating Mixture-of-Experts (MoE) models

Starred by

Created 7 months ago

Updated 3 weeks ago

Qwen-Doc by Tongyi-Zhiwen

548

Long-context reasoning model

Created 1 year ago

Updated 2 months ago

PostTrainBench by aisa-group

463

Automating LLM post-training research and development

Starred by

Created 8 months ago

Updated 6 days ago

chainlit by Chainlit

0.0%

12k

Framework for rapid conversational AI app development

DeepSeek-OCR by deepseek-ai

0.0%

24k

Context-aware OCR model for visual-text compression

Starred by

Created 9 months ago

Updated 6 months ago

NeuralFlow by valine

397

Python script for visualizing Mistral 7B intermediate layer outputs

Created 2 years ago

Updated 1 year ago

MagiAttention by SandAI-org

0.1%

886

Distributed attention mechanism research paper for ultra-long context, heterogeneous data training

Starred by

Created 1 year ago

Updated 8 hours ago

tinker-cookbook by thinking-machines-lab

0.1%

Advanced LLM fine-tuning SDK and example cookbook

Starred by

Created 1 year ago

Updated 1 week ago

torchtitan by pytorch

0.0%

PyTorch platform for generative AI model training research

Starred by

+12

Created 2 years ago

Updated 5 hours ago

checkpoint-engine by MoonshotAI

972

Middleware for efficient LLM weight updates during inference

Starred by

Created 10 months ago

Updated 3 weeks ago

SWE-bench by SWE-bench

Benchmark for evaluating LLMs on real-world GitHub issues

slime by THUDM

0.0%

LLM post-training framework for RL scaling

Step-Audio2 by stepfun-ai

0.1%

End-to-end audio understanding and speech conversation model

Created 1 year ago

Updated 4 months ago

inspect_ai by UKGovernmentBEIS

Framework for large language model evaluations

Starred by

Created 2 years ago

Updated 11 hours ago

openbench by groq

0.1%

789

Provider-agnostic LLM evaluation infrastructure

Starred by

Created 1 year ago

Updated 1 month ago

LaCT by a1600012888

494

Test-Time Training framework for adaptable models

Starred by

Created 1 year ago

Updated 6 months ago

SkyRL by NovaSky-AI

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

ART by OpenPipe

11k

RL library for training LLM agents via GRPO

Starred by

Created 1 year ago

Updated 19 hours ago

torch-profiling-tutorial by Quentin-Anthony

582

PyTorch model profiling tutorial

Created 1 year ago

Updated 11 months ago

OpenHands by OpenHands

82k

AI platform for software development agents

Starred by

+36

Created 2 years ago

Updated 8 hours ago

ERNIE by PaddlePaddle

PaddlePaddle implementations for ERNIE family pre-training models

Starred by

Created 7 years ago

Updated 6 months ago

codex by openai

0.0%

100k

Coding agent CLI tool for terminal-based chat-driven development

Starred by

+38

Created 1 year ago

Updated 7 hours ago

claude-code by anthropics

0.0%

139k

Agentic coding assistant for your terminal

opencode by opencode-ai

0.0%

13k

CLI tool for terminal-based AI coding assistance

Starred by

+11

Created 1 year ago

Updated 10 months ago

gemini-cli by google-gemini

0.0%

106k

AI agent for terminal workflows

MiniMax-M1 by MiniMax-AI

Open-weight reasoning model with hybrid attention

Starred by

Created 1 year ago

Updated 1 year ago

RAGEN by mll-lab-nu

Train LLM agents with reinforcement learning in interactive environments

Starred by

Created 1 year ago

Updated 3 months ago

VoRA by Hon-Wong

388

MLLM with visual capabilities

Created 1 year ago

Updated 1 year ago

awesome-instruction-datasets by jianzhnie

738

Curated list of instruction datasets for training ChatLLMs

Created 3 years ago

Updated 1 month ago

xLAM by SalesforceAIResearch

634

xLAM is a family of large action models for AI agent systems

Starred by

Created 2 years ago

Updated 1 month ago

deer-flow by bytedance

0.0%

78k

Deep research framework combining language models with specialized tools

Starred by

Created 1 year ago

Updated 13 hours ago

arena-hard-auto by lmarena

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

Starred by

Created 2 years ago

Updated 1 year ago

atropos by NousResearch

RL environment framework for LLM trajectory collection/evaluation

Starred by

Created 1 year ago

Updated 3 weeks ago

12-factor-agents by humanlayer

0.0%

25k

Principles for reliable LLM application development

Starred by

Created 1 year ago

Updated 10 months ago

DAPO by BytedTsinghua-SIA

Open-source RL system for large-scale LLM training

Starred by

Created 1 year ago

Updated 1 year ago

system-prompts-and-models-of-ai-tools by x1xhlol

142k

AI tool system prompts and models

rllm by rllm-org

0.1%

Framework for post-training language agents via reinforcement learning

Starred by

Created 1 year ago

Updated 12 hours ago

ring-flash-attention by zhuzilin

FlashAttention extension for ring attention

Starred by

Created 2 years ago

Updated 10 months ago

understand-r1-zero by sail-sg

Research paper analyzing R1-Zero-like training for LLMs

Starred by

Created 1 year ago

Updated 11 months ago

dynamo by ai-dynamo

Inference framework for distributed generative AI model serving

Starred by

Created 1 year ago

Updated 6 hours ago

openai-agents-python by openai

0.1%

28k

Python SDK for multi-agent workflows

OpenManus by FoundationAgents

58k

Open-source framework for building general AI agents

Starred by

Created 1 year ago

Updated 5 months ago

verl by verl-project

23k

RL training library for LLMs

Search-R1 by PeterGriffinJin

RL framework for training LLMs to use search engines

Starred by

Created 1 year ago

Updated 8 months ago

s1 by simplescaling

Test-time scaling recipe for strong reasoning performance

Starred by

Created 1 year ago

Updated 1 year ago

open-r1 by huggingface

26k

SDK for reproducing DeepSeek-R1

openllmetry by traceloop

0.0%

Open-source observability SDK for LLM applications

Kimi-k1.5 by MoonshotAI

Research paper on scaling reinforcement learning with LLMs

Starred by

Created 1 year ago

Updated 1 year ago

UI-TARS by bytedance

0.0%

11k

Multimodal agent for GUI interaction in virtual worlds (research paper)

Starred by

Created 1 year ago

Updated 6 months ago

DeepSeek-R1 by deepseek-ai

92k

Reasoning models research paper

unsloth by unslothai

69k

Finetuning tool for LLMs, targeting speed and memory efficiency

ml-cross-entropy by apple

610

PyTorch module for memory-efficient cross-entropy in LLMs

Starred by

Created 1 year ago

Updated 10 months ago

Liger-Kernel by linkedin

0.0%

Triton kernels for efficient LLM training

Starred by

Created 2 years ago

Updated 15 hours ago

MiniMax-01 by MiniMax-AI

Large language & vision-language models based on linear attention

Starred by

Created 1 year ago

Updated 1 year ago

tabby by TabbyML

34k

Self-hosted AI coding assistant for on-prem code completion

continue by continuedev

0.0%

35k

IDE extension for custom AI code assistants

SkyThought by NovaSky-AI

Training recipes for Sky-T1 family of models

Starred by

Created 1 year ago

Updated 1 year ago

dspy by stanfordnlp

0.0%

36k

Framework for programming language models, not prompting

storm by stanford-oval

0.1%

30k

LLM system for automated knowledge curation and article generation

Starred by

Created 2 years ago

Updated 10 months ago

open-computer-use by e2b-dev

AI agent for computer control via LLMs

Starred by

Created 1 year ago

Updated 2 weeks ago

PaLM-rlhf-pytorch by lucidrains

RLHF implementation on PaLM

Starred by

Created 3 years ago

Updated 13 hours ago

picotron by huggingface

Minimalist distributed training framework for educational use

Starred by

Created 1 year ago

Updated 11 months ago

PRIME by PRIME-RL

Scalable RL solution for advanced reasoning of language models

Starred by

Created 1 year ago

Updated 1 year ago

sglang by sgl-project

31k

Fast serving framework for LLMs and vision language models

DeepSeek-V3 by deepseek-ai

104k

MoE language model research paper with 671B total parameters

Starred by

+13

Created 1 year ago

Updated 11 months ago

gitingest by coderamp-labs

0.0%

15k

CLI tool for LLM-friendly code ingestion from Git repos

Starred by

Created 1 year ago

Updated 5 days ago

tau-bench by sierra-research

Benchmark for tool-agent-user interaction research

Starred by

Created 2 years ago

Updated 4 months ago

genesis-world by Genesis-Embodied-AI

30k

Physics platform for robotics & embodied AI learning

search-and-learn by huggingface

Recipes to scale inference-time compute of open models

Starred by

Created 1 year ago

Updated 2 months ago

open-instruct by allenai

Training codebase for instruction-following language models

desktop by e2b-dev

SDK for virtual desktop sandboxes for LLM-powered computer use

Starred by

Created 2 years ago

Updated 3 days ago

VLMEvalKit by open-compass

Evaluation toolkit for large multi-modality models (LMMs)

Created 2 years ago

Updated 1 week ago

Qwen3-VL by QwenLM

0.0%

20k

Multimodal LLM for vision-language tasks, document parsing, and agent functionality

Starred by

Created 1 year ago

Updated 5 months ago

DocBank by doc-analysis

653

Layout analysis dataset for document understanding tasks

Created 6 years ago

Updated 1 year ago

Qwen-VL by QwenLM

Vision-language model for multimodal understanding, localization, and text reading

Starred by

Created 2 years ago

Updated 2 years ago

OSWorld by xlang-ai

Multimodal agent benchmark for open-ended tasks in realistic computer environments

Starred by

Created 2 years ago

Updated 1 day ago

SoM by microsoft

Visual prompting method for GPT-4V and LMMs

Starred by

Created 2 years ago

Updated 1 year ago

dynasaur by adobe-research

360

LLM agent framework using dynamic action creation via Python code generation

Starred by

Created 1 year ago

Updated 1 year ago

browser-use by browser-use

0.0%

106k

SDK for AI agent browser control

ShowUI by showlab

Vision-language-action model for GUI agent & computer use (CVPR 2025 paper)

Starred by

Created 1 year ago

Updated 3 months ago

WilmerAI by SomeOddCodeGuy

823

AI inference router for specialized workflows

Starred by

Created 2 years ago

Updated 1 week ago

aisuite by andrewyng

0.0%

15k

Unified interface for multiple generative AI providers

Starred by

Created 2 years ago

Updated 6 days ago

servers by modelcontextprotocol

89k

Reference implementations for the Model Context Protocol (MCP) servers

python-sdk by modelcontextprotocol

0.0%

24k

Python SDK for Model Context Protocol (MCP) servers/clients

Starred by

Created 1 year ago

Updated 12 hours ago

every-chatgpt-gui by billmei

Curated list of ChatGPT, Claude, and other LLM front-end GUI clients

Created 3 years ago

Updated 6 months ago

MinerU by opendatalab

0.0%

75k

PDF extraction tool for converting PDFs to Markdown and JSON

Starred by

Created 2 years ago

Updated 4 days ago

Qwen3-Coder by QwenLM

17k

Code LLM for code completion, generation, and assistant use cases

Starred by

Created 2 years ago

Updated 4 months ago

LLMxMapReduce by thunlp

873

Framework for LLM long-sequence processing via MapReduce-inspired divide-and-conquer

Created 1 year ago

Updated 4 months ago

llm-app by pathwaycom

59k

LLM app templates for RAG, AI pipelines, and enterprise search

Starred by

Created 3 years ago

Updated 3 weeks ago

docling by docling-project

0.1%

64k

Prepare documents for generative AI

Qwen3 by QwenLM

27k

Large language model series by Qwen team, Alibaba Cloud

meditron by epfLLM

Open-source medical LLMs adapted from Llama-2

Starred by

Created 2 years ago

Updated 2 years ago

OmniParser by microsoft

0.0%

25k

Screen parsing tool for vision-based GUI agents

Starred by

Created 1 year ago

Updated 1 week ago

fast-apply by kortix-ai

409

Pipeline for data generation and fine-tuning Qwen2.5 Coder models

Starred by

Created 1 year ago

Updated 10 months ago

Emu3 by baaivision

Multimodal model for vision-language understanding and generation

Starred by

Created 1 year ago

Updated 6 months ago

together-cookbook by togethercomputer

Cookbook for open-source models via Together AI

Created 1 year ago

Updated 2 weeks ago

zerox by getomni-ai

12k

OCR SDK for AI ingestion of documents with complex layouts

Starred by

Created 2 years ago

Updated 1 year ago

Janus by deepseek-ai

18k

Unified multimodal model research paper for understanding and generation

Starred by

Created 1 year ago

Updated 1 year ago

TransformerEngine by NVIDIA

Library for Transformer model acceleration on NVIDIA GPUs

Starred by

Created 3 years ago

Updated 12 hours ago

O1-Journey by GAIR-NLP

Research paper on replicating O1 via "journey learning"

Starred by

Created 1 year ago

Updated 1 year ago

chunkr by lumina-ai-inc

0.0%

Document intelligence API for RAG/LLM workflows

Starred by

Created 1 year ago

Updated 3 months ago

zep by getzep

Memory foundation for AI stacks, enabling continuous learning

Starred by

Created 3 years ago

Updated 15 hours ago

ColBERT by stanford-futuredata

Neural search for fast, accurate retrieval over large text collections

Starred by

Created 6 years ago

Updated 9 months ago

optillm by algorithmicsuperintelligence

Optimizing inference proxy for LLMs

Starred by

Created 1 year ago

Updated 1 week ago

LiveCodeBench by LiveCodeBench

912

Benchmark for holistic LLM code evaluation

Starred by

Created 2 years ago

Updated 1 year ago

zml by zml

AI inference stack for production

Starred by

Created 1 year ago

Updated 3 days ago

Awesome-LLM-Strawberry by hijkzzz

Collection of LLM papers, blogs, and projects focused on reasoning techniques

Starred by

Created 1 year ago

Updated 7 months ago

GOT-OCR2.0 by Ucas-HaoranWei

0.0%

OCR research paper for unified end-to-end model

Created 1 year ago

Updated 1 year ago

colpali by illuin-tech

Vision-language model code for document retrieval research

Starred by

Created 2 years ago

Updated 2 weeks ago

SuperPrompt by NeoVertex1

Prompt engineering research for AI agent understanding

Starred by

Created 1 year ago

Updated 3 months ago

rStar by zhentingqi

972

Research paper for improving small LLM reasoning via mutual reasoning

Starred by

Created 2 years ago

Updated 1 year ago

llama-stack-apps by ogx-ai

Agentic app examples built on Llama Stack

Starred by

Created 2 years ago

Updated 11 months ago

ms-swift by modelscope

0.0%

15k

SDK for fine-tuning and deploying LLMs/MLLMs

Starred by

Created 3 years ago

Updated 5 hours ago

InternLM-XComposer by InternLM

Multimodal model for long-context video/audio interactions, image understanding, and composition

Starred by

Created 2 years ago

Updated 1 year ago

DisTrO by NousResearch

Distributed optimizers research paper

Starred by

Created 1 year ago

Updated 9 months ago

llama_cloud_services by run-llama

SDK for LlamaCloud GenAI services

Starred by

Created 2 years ago

Updated 2 months ago

DistillKit by arcee-ai

986

Open-source toolkit for LLM distillation research

Starred by

Created 2 years ago

Updated 2 months ago

flux by black-forest-labs

26k

Inference code for FLUX image generation & editing models

ogx by ogx-ai

Composable building blocks for Llama apps

Starred by

Created 2 years ago

Updated 22 hours ago

MindSearch by InternLM

LLM multi-agent framework for web search (Perplexity AI, SearchGPT)

Starred by

Created 2 years ago

Updated 1 year ago

unstructured by Unstructured-IO

0.0%

15k

ETL solution for structuring unstructured data for language models

VIINA by zhukovyuri

353

Event data system for the 2022 Russian Invasion of Ukraine

Created 4 years ago

Updated 4 days ago

MInference by microsoft

Framework for long-context LLM inference speedup via sparse attention

Starred by

Created 2 years ago

Updated 3 months ago

ultravox by fixie-ai

Multimodal LLM for real-time voice interactions

Starred by

Created 2 years ago

Updated 7 months ago

babilong by booydar

251

LLM evaluation benchmark for long-context reasoning

Starred by

Created 2 years ago

Updated 1 month ago

octo by octo-models

Robot policy for generalist manipulation, trained on 800k trajectories

Starred by

Created 2 years ago

Updated 2 years ago

DeepSeek-Coder-V2 by deepseek-ai

0.0%

Open-source code language model comparable to GPT4-Turbo

Starred by

Created 2 years ago

Updated 8 months ago

MathBlackBox by trotsky1997

Research paper for mathematical reasoning via LLMs

Starred by

Created 2 years ago

Updated 1 year ago

EAGLE by SafeAILab

0.0%

Speculative decoding research paper for faster LLM inference

Starred by

Created 2 years ago

Updated 5 months ago

tianshou by thu-ml

11k

PyTorch RL library for algorithm development and application

Starred by

Created 8 years ago

Updated 3 months ago

gemma-2B-10M by mustafaaljadery

934

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

Starred by

Created 2 years ago

Updated 2 years ago

RULER by NVIDIA

Evaluation suite for long-context language models research paper

Starred by

Created 2 years ago

Updated 5 days ago

VILA by NVlabs

Open-source VLMs for efficient video/multi-image understanding

Starred by

Created 2 years ago

Updated 4 months ago

ThunderKittens by HazyResearch

CUDA kernel framework for fast deep learning primitives

selfcodealign by bigcode-project

323

Research paper for self-alignment in code generation

Starred by

Created 2 years ago

Updated 1 year ago

VAR by FoundationVision

Image generation research paper using visual autoregressive modeling

Starred by

Created 2 years ago

Updated 8 months ago

FlagEmbedding by FlagOpen

12k

Toolkit for retrieval and RAG applications

Starred by

Created 3 years ago

Updated 3 months ago

FILM by microsoft

275

LLM for enhanced context utilization

Created 2 years ago

Updated 2 years ago

PLLaVA by magic-research

669

Research paper for parameter-free LLaVA extension to videos

Created 2 years ago

Updated 2 years ago

cohere-toolkit by cohere-ai

RAG toolkit for LLM application development and deployment

Starred by

Created 2 years ago

Updated 3 months ago

EasyContext by jzhang38

760

Recipes for language model context length extrapolation to 1M tokens

Starred by

Created 2 years ago

Updated 1 year ago

Spec-Bench by hemingkx

401

Benchmark for speculative decoding methods (ACL 2024 paper)

Created 2 years ago

Updated 1 year ago

openai-node by openai

0.0%

11k

TypeScript/JavaScript SDK for the OpenAI API

Starred by

Created 4 years ago

Updated 15 hours ago

llama3 by meta-llama

29k

*Deprecated* minimal example for loading and running Llama 3 models

distilabel by argilla-io

Framework for synthetic data and AI feedback pipelines

Open-Sora-Plan by PKU-YuanGroup

12k

Open-source project aiming to reproduce Sora-like T2V model

Starred by

Created 2 years ago

Updated 4 months ago

LLaVA-UHD by thunlp

423

Efficient native-resolution encoding for multimodal LLMs

Created 2 years ago

Updated 3 weeks ago

higgsfield by higgsfield-ai

ML framework for large model training and GPU orchestration

SWE-agent by SWE-agent

20k

Agent for automated software engineering (NeurIPS 2024)

VoiceCraft by jasonppy

Zero-shot speech editing and TTS research paper

Starred by

Created 2 years ago

Updated 1 month ago

Open-Sora by hpcaitech

29k

Video generation initiative for efficient, high-quality video production

Starred by

Created 2 years ago

Updated 3 months ago

bark by suno-ai

0.0%

39k

Generative audio model for realistic speech and sound effects

pal by reasoning-machines

525

Program-aided language model for reasoning tasks

Starred by

Created 3 years ago

Updated 3 years ago

torchtune by meta-pytorch

PyTorch library for LLM post-training and experimentation

self-rag by AkariAsai

Self-RAG implementation for learning retrieval, generation, and critique via self-reflection

Starred by

Created 2 years ago

Updated 2 years ago

OpenPipe by OpenPipe

0.0%

Fine-tuning platform for cheaper models

Starred by

Created 3 years ago

Updated 2 years ago

LLM-Blender by yuchenlin

990

LLM ensembling framework using pairwise ranking and generative fusion

Starred by

Created 3 years ago

Updated 1 year ago

grok-1 by xai-org

0.0%

52k

JAX example code for loading and running Grok-1 open-weights model

aici by microsoft

AICI constrains LLM output using (Wasm) programs

Starred by

Created 2 years ago

Updated 1 year ago

based by HazyResearch

256

Efficient linear attention language models balancing recall and throughput

Starred by

Created 2 years ago

Updated 1 year ago

Yi by 01-ai

Open-source bilingual LLMs trained from scratch

Starred by

Created 2 years ago

Updated 1 year ago

anthropic-tools by anthropics

407

SDK for tool/function calling with Anthropic models (research preview)

Starred by

Created 2 years ago

Updated 1 year ago

self-rewarding-lm-pytorch by lucidrains

Training framework for self-rewarding language models

Starred by

Created 2 years ago

Updated 2 years ago

OpenCodeInterpreter by OpenCodeInterpreter

Open-source code generation system for bridging LLMs and code interpreters

Starred by

Created 2 years ago

Updated 2 years ago

LWM by LargeWorldModel

Multimodal autoregressive model for long-context video/text

Starred by

Created 2 years ago

Updated 1 year ago

ai by vercel

0.1%

26k

AI SDK for building AI-powered applications and agents

SPIN by uclaml

Self-Play Fine-Tuning (SPIN) research paper implementation

Starred by

Created 2 years ago

Updated 2 years ago

trigger.dev by triggerdotdev

0.0%

16k

Open-source platform for background jobs and AI workflows

Starred by

Created 3 years ago

Updated 5 hours ago

AgentBoard by hkust-nlp

426

Analytical evaluation board for multi-turn LLM agents

Starred by

Created 2 years ago

Updated 2 years ago

sparrow by katanaml

Data processing & instruction calling tool using ML, LLM, and Vision LLM

Starred by

Created 4 years ago

Updated 4 weeks ago

search_with_lepton by leptonai

Conversational search engine demo

Starred by

Created 2 years ago

Updated 7 months ago

autogen by microsoft

60k

Agentic framework for multi-agent AI applications

tldraw by tldraw

0.0%

49k

Infinite canvas SDK for building interactive web applications

m2 by HazyResearch

564

Sub-quadratic architecture research paper

Starred by

Created 3 years ago

Updated 1 year ago

mergekit by arcee-ai

CLI tool for merging pretrained language models, combining strengths without retraining

ToolAlpaca by tangqiaoyu

880

Tool-learning framework for language models, research paper

Starred by

Created 3 years ago

Updated 1 year ago

ToolBench by OpenBMB

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

Starred by

Created 3 years ago

Updated 1 year ago

NexusRaven by nexusflowai

326

Evaluation framework for function-calling LLM, NexusRaven-13B

Starred by

Created 2 years ago

Updated 2 years ago

gpt4free by xtekky

66k

API package for multi-provider LLM requests (GPT-4.1, Gemini 2.5, Deepseek R1)

Starred by

Created 3 years ago

Updated 2 days ago

promptbench by microsoftarchive

LLM evaluation framework

Starred by

Created 3 years ago

Updated 5 months ago

spinningup by openai

12k

Educational resource for learning deep reinforcement learning

MiniGPT-4 by Vision-CAIR

26k

Vision-language model for multi-task learning

LLMCompiler by SqueezeAILab

LLM compiler for parallel function calling

Starred by

Created 2 years ago

Updated 2 years ago

NexusRaven-V2 by nexusflowai

419

Open-source LLM for function calling, outperforming GPT-4 in some cases

Starred by

Created 2 years ago

Updated 2 years ago

mamba by state-spaces

19k

Mamba SSM architecture for sequence modeling

gpt-fast by meta-pytorch

PyTorch text generation for efficient transformer inference

Starred by

+20

Created 2 years ago

Updated 11 months ago

generative-models by Stability-AI

27k

Generative models SDK for video, image, and 3D synthesis research

Starred by

Created 3 years ago

Updated 7 months ago

LLM-Shearing by princeton-nlp

641

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

Starred by

Created 2 years ago

Updated 2 years ago

TensorRT-LLM by NVIDIA

0.0%

14k

LLM inference optimization SDK for NVIDIA GPUs

gpt-crawler by BuilderIO

22k

CLI tool for site crawling to generate custom GPT knowledge files

Starred by

Created 2 years ago

Updated 1 year ago

draw-a-ui by SawyerHood

14k

Web app generates HTML from UI wireframes

Starred by

Created 2 years ago

Updated 1 year ago

openinterpreter by openinterpreter

0.0%

67k

Natural language interface for computers

LLaVA-Plus-Codebase by LLaVA-VL

769

Multimodal agent for vision tasks using external tools

Starred by

Created 2 years ago

Updated 2 years ago

opengpts by langchain-ai

Open-source platform for building custom GPT assistants

Starred by

Created 2 years ago

Updated 1 year ago

openchat by imoneoi

Open-source LLM fine-tuned with C-RLFT, inspired by offline reinforcement learning

Starred by

Created 3 years ago

Updated 1 year ago

CLIP by openai

34k

Image-text matching model for zero-shot prediction

LLaVA by haotian-liu

25k

Multimodal assistant with GPT-4 level capabilities

llmperf by ray-project

LLM validation/benchmark library for LLM APIs

Starred by

Created 2 years ago

Updated 1 year ago

LightLLM by ModelTC

Python framework for LLM inference and serving

Starred by

Created 3 years ago

Updated 5 hours ago

examples by graphcore

333

ML examples for Graphcore IPUs, training and inference

Starred by

Created 8 years ago

Updated 2 years ago

streaming-llm by mit-han-lab

Framework for efficient LLM streaming

Starred by

Created 2 years ago

Updated 2 years ago

mistral-inference by mistralai

11k

Inference library for Mistral models

Starred by

Created 2 years ago

Updated 1 month ago

can-ai-code by the-crypt-keeper

597

AI coding model evaluation framework

Starred by

Created 3 years ago

Updated 1 year ago

LongLoRA by JIA-Lab-research

LongLoRA: Efficient fine-tuning for long-context LLMs

Starred by

Created 2 years ago

Updated 1 year ago

Qwen by QwenLM

0.0%

21k

Chat & pretrained LLM by Alibaba Cloud

ollama by ollama

177k

CLI tool for running LLMs locally

alpaca_farm by tatsu-lab

845

RLHF simulation framework for accessible instruction-following/alignment research

Starred by

Created 3 years ago

Updated 2 years ago

Medusa by FasterDecoding

Framework for accelerating LLM generation using multiple decoding heads

Starred by

Created 2 years ago

Updated 2 years ago

adept-inference by persimmon-ai-labs

411

Inference code for the Persimmon-8B LLM

Starred by

Created 2 years ago

Updated 2 years ago

butterfish by bakks

538

CLI tool for adding AI to your shell

Starred by

Created 3 years ago

Updated 1 month ago

shell_gpt by TheR1D

12k

CLI tool for shell command generation and task automation using LLMs

Starred by

Created 3 years ago

Updated 3 weeks ago

LocalAI by mudler

48k

Open-source OpenAI alternative for local AI inference

legalbench by HazyResearch

614

Legal reasoning benchmark for evaluating LLMs

Created 3 years ago

Updated 4 months ago

yarn by jquesnelle

Context window extension method for LLMs (research paper, models)

Starred by

Created 3 years ago

Updated 2 years ago

shell-ai by ricklamers

CLI tool for natural language to shell command translation

Created 2 years ago

Updated 10 months ago

llama-cookbook by meta-llama

18k

Guide for building with Llama models

codellama by meta-llama

16k

Inference code for CodeLlama models

prm800k by openai

Dataset of LLM solutions to math problems with step-level correctness labels

Starred by

Created 3 years ago

Updated 3 years ago

FLAML by microsoft

AutoML library for efficient machine learning and AI operations

Starred by

Created 6 years ago

Updated 1 day ago

engshell by emcf

English-language shell for OS, powered by LLMs

Starred by

Created 3 years ago

Updated 5 months ago

WizardLM by nlpxucan

LLMs built using Evol-Instruct for complex instruction following

sqlcoder by defog-ai

LLM for natural language to SQL conversion

Starred by

Created 2 years ago

Updated 2 years ago

QuIP by Cornell-RelaxML

0.3%

400

Code for LLM quantization research

Created 3 years ago

Updated 2 years ago

lmdeploy by InternLM

Toolkit for LLM compression, deployment, and serving

Starred by

Created 3 years ago

Updated 5 hours ago

flexflow-train by flexflow

Accelerating distributed deep learning training

Starred by

Created 7 years ago

Updated 3 weeks ago

Platypus by arielnlee

625

Code for fine-tuning LLMs using LoRA

Starred by

Created 3 years ago

Updated 2 years ago

MetaGPT by FoundationAgents

0.0%

69k

Multi-agent framework for collaborative AI software development

outlines by dottxt-ai

0.0%

15k

SDK for structured LLM text generation

Chinese-Llama-2-7b by LinkSoul-AI

Chinese Llama 2 model for chat, fully open-source and commercially available

Created 3 years ago

Updated 2 years ago

sentence-transformers by huggingface

19k

Framework for text embeddings, retrieval, and reranking

private-gpt by zylon-ai

57k

Private AI API for local document interaction using LLMs

swiss_army_llama by Dicklesworthstone

FastAPI service for semantic text search using precomputed embeddings

Starred by

Created 3 years ago

Updated 1 year ago

transformers-tutorials by abhimishra91

863

Tutorials for fine-tuning transformer models on NLP tasks

Starred by

Created 6 years ago

Updated 2 years ago

bert by google-research

40k

TensorFlow code and pre-trained models for BERT

ALCE by princeton-nlp

522

Benchmark for evaluating LLMs' citation abilities

Starred by

Created 3 years ago

Updated 1 year ago

lorahub by sail-sg

671

Framework for efficient cross-task generalization via dynamic LoRA composition

Starred by

Created 3 years ago

Updated 2 years ago

text-to-text-transfer-transformer by google-research

Unified text-to-text transformer for NLP research

chatbot by vercel

21k

Next.js chatbot template for building AI-powered chat applications

Starred by

Created 3 years ago

Updated 2 weeks ago

OpenChatKit by togethercomputer

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

clownfish by newhouseb

327

Constrained decoding for LLMs against JSON schema

Starred by

Created 3 years ago

Updated 3 years ago

stanford_alpaca by tatsu-lab

30k

Instruction-following LLaMA model training and data generation

deep-learning-pytorch-huggingface by philschmid

Tutorials for deep learning with PyTorch and Hugging Face libraries

Starred by

Created 3 years ago

Updated 1 year ago

xTuring by stochasticai

SDK for fine-tuning and customizing open-source LLMs

Starred by

Created 3 years ago

Updated 4 months ago

LMOps by microsoft

0.0%

AI research initiative for building AI products with foundation models

Starred by

Created 3 years ago

Updated 1 week ago

DialogStudio by salesforce

526

Unified dataset for conversational AI research

Created 3 years ago

Updated 1 month ago

ggml by ggml-org

0.1%

15k

Tensor library for machine learning

H2O by FMInference

530

KV cache eviction research paper for efficient LLM inference

Starred by

Created 3 years ago

Updated 2 years ago

h2ogpt by h2oai

12k

Private chat with local GPT with document, images, video, etc

Starred by

Created 3 years ago

Updated 9 months ago

qlora by artidoro

0.0%

11k

Finetuning tool for quantized LLMs

LlamaFactory by hiyouga

73k

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

long_llama by CStanKonrad

LLM for long context handling, fine-tuned with Focused Transformer

Starred by

Created 3 years ago

Updated 2 years ago

self-instruct by yizhongw

Self-Instruct: Research paper for aligning language models with self-generated instructions

Starred by

Created 3 years ago

Updated 3 years ago

llama-cpp-python by abetlen

11k

Python bindings for llama.cpp, enabling local LLM inference

helm by stanford-crfm

Open-source Python framework for holistic evaluation of foundation models

text-generation-inference by huggingface

11k

Rust/Python/gRPC server for fast LLM text generation

alpaca_lora_4bit by johnsmith0031

534

Fine-tuning and inference tool for quantized LLaMA models

Starred by

Created 3 years ago

Updated 2 years ago

minimal-llama by zphang

456

Code for running and fine-tuning LLaMA models

Starred by

Created 3 years ago

Updated 2 years ago

LongChat by DachengLi1

536

Long-context LLM chatbot training and evaluation framework

Starred by

Created 3 years ago

Updated 2 years ago

exllama by turboderp

Llama implementation for memory-efficient quantized weights

Starred by

Created 3 years ago

Updated 2 years ago

LMFlow by OptimalScale

Toolkit for finetuning and inference of large foundation models

Starred by

Created 3 years ago

Updated 2 months ago

vllm by vllm-project

0.0%

87k

LLM serving engine for high-throughput, memory-efficient inference

openai-python by openai

31k

Python SDK for the OpenAI API

starcoder by bigcode-project

Code LM for code generation and instruction fine-tuning

axolotl by axolotl-ai-cloud

12k

CLI tool for streamlined post-training of AI models

hnswlib by nmslib

0.0%

Header-only C++ library for fast approximate nearest neighbors

Starred by

+13

Created 9 years ago

Updated 4 months ago

open_clip by mlfoundations

14k

OpenCLIP: open-source CLIP implementation for vision-language representation learning

accelerate by huggingface

0.0%

10k

PyTorch training helper for distributed execution

SpQR by Vahe1994

554

Weight compression research paper for near-lossless LLM quantization

Starred by

Created 3 years ago

Updated 5 months ago

AutoGPTQ by AutoGPTQ

LLM quantization package using GPTQ algorithm

llm-awq by mit-han-lab

Weight quantization research paper for LLM compression/acceleration

Starred by

Created 3 years ago

Updated 1 year ago

Alpaca-CoT by PhoebusSi

IFT platform for instruction collection, parameter-efficient methods, and LLMs

Starred by

Created 3 years ago

Updated 2 years ago

baize-chatbot by project-baize

Chat model trained via LoRA, using ChatGPT-generated dialogs

Starred by

Created 3 years ago

Updated 2 years ago

falcontune by rmihaylov

462

CLI tool for finetuning Falcon LLMs

Starred by

Created 3 years ago

Updated 2 years ago

gorilla by ShishirPatil

13k

LLM tool-use framework for API invocation and function calling

MeZO by princeton-nlp

Research paper implementation for memory-efficient LM fine-tuning

Starred by

Created 3 years ago

Updated 2 years ago

lm-evaluation-harness by EleutherAI

0.0%

13k

Framework for few-shot language model evaluation

llama.cpp by ggml-org

0.0%

121k

C/C++ library for local LLM inference

GPTCache by zilliztech

Semantic cache for LLM queries, integrated with LangChain and LlamaIndex

Starred by

Created 3 years ago

Updated 1 year ago

tree-of-thoughts by kyegomez

Plug-and-play implementation of Tree of Thoughts for LLM reasoning

Starred by

Created 3 years ago

Updated 1 year ago

gpt-neox by EleutherAI

Framework for training large-scale autoregressive language models

pythia by EleutherAI

0.1%

LLM suite for interpretability, learning dynamics, ethics, and transparency research

Starred by

Created 4 years ago

Updated 8 months ago

llm-foundry by mosaicml

LLM training code for Databricks foundation models

sd-webui-controlnet by Mikubill

18k

WebUI extension for ControlNet, an image-generation plugin

Starred by

Created 3 years ago

Updated 1 year ago

ControlNet by lllyasviel

34k

Neural network structure for adding conditional control to diffusion models

RWKV-LM by BlinkDL

0.0%

15k

RNN for LLM, transformer-level performance, parallelizable training

basaran by hyperonym

Open-source API server for text completion

Starred by

Created 3 years ago

Updated 2 years ago

pandas-ai by sinaptik-ai

24k

Python SDK for conversational data analysis using LLMs and RAG

Starred by

Created 3 years ago

Updated 9 months ago

guidance by guidance-ai

22k

Guidance is a programming paradigm for steering LLMs

raft by NVIDIA

CUDA-accelerated primitives for ML/data mining algorithms

Starred by

Created 7 years ago

Updated 21 hours ago

lit-llama by Lightning-AI

LLaMA implementation for pretraining, finetuning, and inference

Starred by

Created 3 years ago

Updated 1 year ago

civitai by civitai

Platform for sharing AI models

Starred by

Created 3 years ago

Updated 10 hours ago

LyCORIS by KohakuBlueleaf

Parameter-efficient fine-tuning algorithms for Stable Diffusion

Created 3 years ago

Updated 5 days ago

stable-diffusion-webui by AUTOMATIC1111

164k

Web UI for Stable Diffusion

flash-attention by Dao-AILab

0.0%

25k

Fast, memory-efficient attention implementation

LoRA by microsoft

14k

PyTorch library for low-rank adaptation (LoRA) of LLMs

EditAnything by sail-sg

Image editing research paper using segmentation and diffusion

Starred by

Created 3 years ago

Updated 1 year ago

ImageBind by facebookresearch

PyTorch implementation for multimodal embeddings research paper

Starred by

Created 3 years ago

Updated 8 months ago

langchain by langchain-ai

142k

Framework for building LLM-powered applications

open-llms by eugeneyan

13k

Curated list of commercially-usable open LLMs

Starred by

Created 3 years ago

Updated 1 year ago

IF by deep-floyd

Text-to-image model for photorealistic synthesis and language understanding

Starred by

Created 3 years ago

Updated 2 years ago

EasyLM by young-geng

LLM training/finetuning framework in JAX/Flax

Starred by

Created 3 years ago

Updated 1 year ago

open_llama by openlm-research

Open-source reproduction of LLaMA models

LLaMA-Adapter by OpenGVLab

Efficient fine-tuning for instruction-following LLaMA models

Starred by

Created 3 years ago

Updated 2 years ago

bitsandbytes by bitsandbytes-foundation

PyTorch library for k-bit quantization, enabling accessible LLMs

composer by mosaicml

DL framework for training at scale, optimized for large-scale clusters

fairseq by facebookresearch

32k

Sequence modeling toolkit for translation, language modeling, and text generation research

Starred by

+42

Created 9 years ago

Updated 10 months ago

alpaca-lora by tloen

19k

LoRA fine-tuning for LLaMA

web-llm by mlc-ai

0.0%

18k

In-browser LLM inference engine using WebGPU for hardware acceleration

transformers by huggingface

163k

ML library for pretrained model inference and training

Awesome-LLM by Hannibal046

27k

Curated list of Large Language Model resources

Starred by

Created 3 years ago

Updated 1 year ago

reins by pegasi-ai

407

AI testing framework for LLM output validation

Created 3 years ago

Updated 2 months ago

trl by huggingface

0.0%

19k

Library for transformer RL

peft by huggingface

21k

Parameter-efficient fine-tuning (PEFT) library

annotated_deep_learning_paper_implementations by labmlai

67k

PyTorch implementations/tutorials of deep learning papers with side-by-side notes

Starred by

Created 6 years ago

Updated 6 months ago

Megatron-LM by NVIDIA

0.0%

17k

Framework for training transformer models at scale

minGPT by karpathy

25k

Minimal PyTorch re-implementation for GPT training and inference

nanoGPT by karpathy

0.0%

61k

Minimalist repo for training/finetuning GPT models

llama by meta-llama

60k

Inference code for Llama 2 models (deprecated)

RedPajama-Data by togethercomputer

0.0%

Dataset pipeline for training large language models

Starred by

Created 3 years ago

Updated 1 month ago

FasterTransformer by NVIDIA

Optimized transformer library for inference

dolly by databrickslabs

11k

Instruction-following LLM trained on the Databricks Machine Learning Platform

StableLM by Stability-AI

0.0%

16k

Language models by Stability AI

FastChat by lm-sys

39k

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

web-stable-diffusion by mlc-ai

Browser-based Stable Diffusion demo with no server support

Starred by

Created 3 years ago

Updated 2 years ago

DeepSpeed by deepspeedai

43k

Deep learning optimization library for distributed training and inference

llama_index by run-llama

51k

Data framework for building LLM-powered agents

ColossalAI by hpcaitech

41k

AI system for large-scale parallel training

DeepLearningExamples by NVIDIA

15k

Deep learning examples for training and deployment

Starred by

Created 8 years ago

Updated 1 year ago

tensorflow by tensorflow

0.0%

196k

Open-source ML framework

Feedback? Help us improve.