Johannes Hagemann

LLM-generated proofs for math olympiads

Starred by

Daniel Han(Cofounder of Unsloth).

openai-imo-2025-proofs by aw31

1.1%

470

created 4 weeks ago

updated 4 weeks ago

Starred by

Shizhe Diao(Research Scientist at NVIDIA; Author of LMFlow),

Vincent Weisser(Cofounder of Prime Intellect), and

1 more.

mle-bench by openai

0.9%

848

Benchmark for evaluating AI agents on machine learning engineering tasks

Communication protocol for cost-efficient LLM collaboration

Starred by

Jeffrey Morgan(Cofounder of Ollama) and

Michael Chiang(Cofounder of Ollama).

minions by HazyResearch

1.1%

Starred by

Tobi Lutke(Cofounder of Shopify),

Elie Bursztein(Cybersecurity Lead at Google DeepMind), and

1 more.

pyspur by PySpur-Dev

Visual playground for agentic workflows, enabling faster iteration

RL environment framework for LLM trajectory collection/evaluation

Starred by

Georgios Konstantopoulos(CTO, General Partner at Paradigm),

Thomas Wolf(Cofounder of Hugging Face), and

1 more.

atropos by NousResearch

1.4%

585

created 3 months ago

Terminal app for managing multiple AI agents

Starred by

Donny Kang(Author of SWC; Maintainer of Turbopack),

Beyang Liu(Cofounder of Sourcegraph), and

3 more.

claude-squad by smtg-ai

4.2%

RL for LLMs in verifiable environments

Starred by

Will Brown(Research Lead at Prime Intellect),

Junyang Lin(Core Maintainer of Alibaba Qwen), and

3 more.

verifiers by willccbb

2.4%

DualPipe by deepseek-ai

Pipeline parallelism algorithm for training large models

updated 5 months ago

Starred by

Patrick von Platen(Research Engineer at Mistral; Author of Hugging Face Diffusers),

Chaoyu Yang(Founder of Bento), and

2 more.

DeepGEMM by deepseek-ai

CUDA library for efficient FP8 GEMM kernels with fine-grained scaling

Starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Jeffrey Morgan(Cofounder of Ollama), and

4 more.

FlashMLA by deepseek-ai

Efficient CUDA kernels for MLA decoding

Starred by

Chris Lattner(Cofounder of Modular; Author of LLVM, Clang, Swift, Mojo, MLIR),

Vincent Weisser(Cofounder of Prime Intellect), and

14 more.

open-infra-index by deepseek-ai

AI infrastructure tools for efficient AGI development

Starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Vincent Weisser(Cofounder of Prime Intellect), and

2 more.

open-thoughts by open-thoughts

Open dataset for training reasoning models

Procedural dataset generator for reasoning models

Starred by

Shizhe Diao(Research Scientist at NVIDIA; Author of LMFlow),

Junyang Lin(Core Maintainer of Alibaba Qwen), and

4 more.

reasoning-gym by open-thought

1.8%

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), and

8 more.

TinyZero by Jiayi-Pan

Minimal reproduction of DeepSeek R1 Zero for countdown/multiplication tasks

Starred by

Jason Knight(Director AI Compilers at NVIDIA; Cofounder of OctoML),

Vincent Weisser(Cofounder of Prime Intellect), and

8 more.

verl by volcengine

2.2%

RL training library for LLMs

created 9 months ago

Starred by

Vincent Weisser(Cofounder of Prime Intellect),

Lewis Tunstall(Research Engineer at Hugging Face), and

4 more.

PRIME by PRIME-RL

Scalable RL solution for advanced reasoning of language models

created 7 months ago

updated 5 months ago

Starred by

Vincent Weisser(Cofounder of Prime Intellect).

magnetron by MarioSieg

558

Minimalist PyTorch alternative for research/production

created 7 months ago

Starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Georgios Konstantopoulos(CTO, General Partner at Paradigm), and

1 more.

torchft by pytorch

PyTorch library for fault-tolerant distributed training

381

GPU monitoring/diagnostics tool for AI/ML workloads

gpud by leptonai

1.0%

412

OML-1.0-Fingerprinting by sentient-agi

Tooling for LLM fingerprinting via fine-tuning, enabling model ownership verification

created 9 months ago

Starred by

Shizhe Diao(Research Scientist at NVIDIA; Author of LMFlow).

Awesome-LLM-Strawberry by hijkzzz

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

created 11 months ago

Bibliography for OpenAI's o1 project

Starred by

Jason Knight(Director AI Compilers at NVIDIA; Cofounder of OctoML),

Tim J. Baek(Founder of Open WebUI), and

4 more.

awesome-o1 by srush

Language model training speedrun on 8x H100 GPUs

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), and

7 more.

modded-nanogpt by KellerJordan

1.3%

updated 4 weeks ago

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Vincent Weisser(Cofounder of Prime Intellect), and

8 more.

entropix by xjdr-alt

Research project for entropy-based context-aware sampling & parallel CoT decoding

Starred by

Ishaan Jaffer(Cofounder of LiteLLM),

Andrew Kane(Author of pgvector), and

5 more.

infinity by michaelfeil

REST API for high-throughput, low-latency embedding and reranking

Starred by

Tobi Lutke(Cofounder of Shopify),

Tim J. Baek(Founder of Open WebUI), and

2 more.

ell by MadcowD

Lightweight prompt engineering framework

Triton kernels for efficient LLM training

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Jiayi Pan(Author of SWE-Gym; MTS at xAI), and

8 more.

Liger-Kernel by linkedin

0.8%

Starred by

Vincent Weisser(Cofounder of Prime Intellect).

ADAS by ShengranHu

Automated agentic system design via meta-agent search (ICLR 2025 paper)

Starred by

Omar Sanseviero(DevRel at Google DeepMind) and

Stas Bekman(Author of "Machine Learning Engineering Open Book"; Research Engineer at Snowflake).

cookbook by EleutherAI

Deep learning resource for practical model work

812

Starred by

Phil Wang(Prolific Research Paper Implementer) and

Vincent Weisser(Cofounder of Prime Intellect).

system-2-research by open-thought

Reasoning resources for AI systems, agents, and cognitive architectures

851

updated 5 months ago

Starred by

Travis Fischer(Founder of Agentic),

Omar Sanseviero(DevRel at Google DeepMind), and

4 more.

llamacoder by Nutlope

Open-source tool generates small apps from a single prompt

Starred by

Vincent Weisser(Cofounder of Prime Intellect) and

Wing Lian(Founder of Axolotl AI).

DistillKit by arcee-ai

Open-source toolkit for LLM distillation research

708

Fast serving framework for LLMs and vision language models

Starred by

Elie Bursztein(Cybersecurity Lead at Google DeepMind),

Philipp Schmid(DevRel at Google DeepMind), and

25 more.

sglang by sgl-project

1.3%

17k

Reasoning tasks collection for LLMs

Starred by

Wing Lian(Founder of Axolotl AI),

Philipp Schmid(DevRel at Google DeepMind), and

4 more.

Open-Reasoning-Tasks by NousResearch

448

updated 10 months ago

Starred by

Tobi Lutke(Cofounder of Shopify),

Vincent Weisser(Cofounder of Prime Intellect), and

2 more.

llama-stack-apps by llamastack

Agentic app examples built on Llama Stack

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

Starred by

Wing Lian(Founder of Axolotl AI).

SPPO by uclaml

574

Starred by

Anton Troynikov(Cofounder of Chroma),

Jeff Hammerbacher(Cofounder of Cloudera), and

3 more.

OpenDiloco by PrimeIntellect-ai

Framework for globally distributed low-communication training

524

CLI tool for converting PDFs and other documents to Markdown, JSON, and HTML

updated 7 months ago

Starred by

Ben Firshman(Cofounder of Replicate),

Joe Walnes(Head of Experimental Projects at Stripe), and

11 more.

marker by datalab-to

2.3%

28k

Starred by

Vincent Weisser(Cofounder of Prime Intellect),

Jared Palmer(Ex-VP AI at Vercel; Founder of Turborepo; Author of Formik, TSDX), and

10 more.

LLM101n by karpathy

Educational resource for building a Storyteller AI LLM

34k

Starred by

Lewis Tunstall(Research Engineer at Hugging Face),

Patrick von Platen(Research Engineer at Mistral; Author of Hugging Face Diffusers), and

10 more.

torchtune by pytorch

PyTorch library for LLM post-training and experimentation

Starred by

Matei Zaharia(Cofounder of Databricks),

Yaowei Zheng(Author of LLaMA-Factory), and

13 more.

megablocks by databricks

Lightweight library for mixture-of-experts (MoE) training

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Elvis Saravia(Founder of DAIR.AI), and

17 more.

grok-1 by xai-org

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

50k

updated 11 months ago

Starred by

Andre Zayarni(Cofounder of Qdrant),

Chenlin Meng(Cofounder of Pika), and

2 more.

docarray by docarray

Python library for multimodal data representation, transmission, storage, and retrieval

Finetuning tool for LLMs, targeting speed and memory efficiency

Starred by

Tobi Lutke(Cofounder of Shopify),

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), and

25 more.

unsloth by unslothai

1.2%

44k

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), and

27 more.

mlx by ml-explore

Array framework for machine learning on Apple silicon

22k

Starred by

Jeff Hammerbacher(Cofounder of Cloudera) and

Wing Lian(Founder of Axolotl AI).

resource-stream by gpu-mode

CUDA resource collection for GPU programming

updated 7 months ago

Starred by

Amanpreet Singh(Cofounder of Contextual AI).

DRUGS by EGjoni

Inference technique for increasing variety in generative models

353

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

NexusRaven-V2 by nexusflowai

415

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Zhiyuan Li(Cofounder of Nexa AI), and

18 more.

mamba by state-spaces

Mamba SSM architecture for sequence modeling

updated 4 weeks ago

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Tobi Lutke(Cofounder of Shopify), and

18 more.

skypilot by skypilot-org

Framework for cloud AI/batch jobs, unifying execution across diverse infrastructure

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Lianmin Zheng(Author of SGLang), and

15 more.

gpt-fast by meta-pytorch

PyTorch text generation for efficient transformer inference

updated 4 months ago

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Anil Dash(Former CEO of Glitch), and

18 more.

llamafile by Mozilla-Ocho

Single-file LLM distribution and runtime via `llama.cpp` and Cosmopolitan Libc

23k

Starred by

Wing Lian(Founder of Axolotl AI),

Yaowei Zheng(Author of LLaMA-Factory), and

1 more.

MergeLM by yule-BUAA

Codebase for merging language models via parameter averaging

843

Starred by

Vincent Weisser(Cofounder of Prime Intellect),

Michael Han(Cofounder of Unsloth), and

19 more.

text-generation-webui by oobabooga

Web UI for LLM text generation

45k

Starred by

Wing Lian(Founder of Axolotl AI),

Yaowei Zheng(Author of LLaMA-Factory), and

2 more.

LLMTest_NeedleInAHaystack by gkamradt

LLM testing tool for evaluating in-context retrieval accuracy

Agent orchestration framework for building controllable agents

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Didier Lopes(Founder of OpenBB), and

2 more.

langgraph by langchain-ai

1.8%

17k

Starred by

Shizhe Diao(Research Scientist at NVIDIA; Author of LMFlow),

Ying Sheng(Author of SGLang), and

15 more.

mergekit by arcee-ai

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

Autonomous agent for web/local research, generating cited reports

Starred by

Emile Vauge(Founder of Traefik),

Anton Troynikov(Cofounder of Chroma), and

7 more.

gpt-researcher by assafelovic

0.8%

23k

updated 4 days ago

Starred by

Jason Knight(Director AI Compilers at NVIDIA; Cofounder of OctoML),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

5 more.

lorax by predibase

Multi-LoRA inference server for serving 1000s of fine-tuned LLMs

Agent for unified data, modular design, and open-source LLMs

Starred by

Vincent Weisser(Cofounder of Prime Intellect).

lumos by allenai

468

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Wing Lian(Founder of Axolotl AI), and

3 more.

S-LoRA by S-LoRA

System for scalable LoRA adapter serving

Starred by

Will Brown(Research Lead at Prime Intellect),

Vincent Weisser(Cofounder of Prime Intellect), and

3 more.

loom by socketteer

Tree-based writing interface for human-AI collaboration

Starred by

Elie Bursztein(Cybersecurity Lead at Google DeepMind),

Ankush Gola(Cofounder of LangChain), and

2 more.

opengpts by langchain-ai

Open-source platform for building custom GPT assistants

PyTorch tool for pipeline parallelism

Starred by

Yang Song(Professor at Caltech; Research Scientist at OpenAI),

Jeremy Howard(Cofounder of fast.ai), and

4 more.

PiPPy by pytorch

774

updated 11 months ago

Starred by

Tobi Lutke(Cofounder of Shopify),

Jonathan Ragan-Kelley(Professor at MIT), and

16 more.

ml-engineering by stas00

Open book for LLM/VLM training engineers

Starred by

Tim J. Baek(Founder of Open WebUI),

Lewis Tunstall(Research Engineer at Hugging Face), and

6 more.

chat-ui by huggingface

Chat UI: open-source interface for LLMs

Starred by

Tobi Lutke(Cofounder of Shopify),

Patrick von Platen(Research Engineer at Mistral; Author of Hugging Face Diffusers), and

20 more.

axolotl by axolotl-ai-cloud

CLI tool for streamlined post-training of AI models

10k

Starred by

Peter Norvig(Author of "Artificial Intelligence: A Modern Approach"; Research Director at Google),

Michael Han(Cofounder of Unsloth), and

20 more.

open-interpreter by openinterpreter

Natural language interface for computers

60k

Starred by

Boris Cherny(Creator of Claude Code; MTS at Anthropic),

Nat Friedman(Former CEO of GitHub), and

27 more.

aider by Aider-AI

AI pair programming in your terminal

37k

Starred by

Vincent Weisser(Cofounder of Prime Intellect),

Elvis Saravia(Founder of DAIR.AI), and

1 more.

AgentTuning by THUDM

Agent tuning for generalized LLM agent abilities

LLM framework for RAG and data creation

Starred by

Omar Sanseviero(DevRel at Google DeepMind),

Jeff Hammerbacher(Cofounder of Cloudera), and

2 more.

synthesizer by SciPhi-AI

628

Starred by

Aravind Srinivas(Cofounder of Perplexity),

Jeff Hammerbacher(Cofounder of Cloudera), and

15 more.

apex by NVIDIA

PyTorch extension for streamlined mixed precision & distributed training

created 7 years ago

Starred by

Hiroshi Shibata(Core Contributor to Ruby),

Yaowei Zheng(Author of LLaMA-Factory), and

41 more.

ray by ray-project

AI compute engine for scaling Python and AI applications

38k

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

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Clement Delangue(Cofounder of Hugging Face), and

41 more.

vllm by vllm-project

1.4%

55k

LLM microservice web framework (maintenance mode)

lanarky by ajndkr

994

Starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

2 more.

hyena-dna by HazyResearch

Genomic foundation model for long-range DNA sequence modeling

707

Starred by

Sourabh Bajaj(Cofounder of Uplimit),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

2 more.

NextChat by ChatGPTNextWeb

AI assistant for web, iOS, MacOS, Android, Linux, and Windows

85k

LangChain implementation of ChatGPT Code Interpreter

updated 6 days ago

Starred by

Jeremy Howard(Cofounder of fast.ai),

Travis Fischer(Founder of Agentic), and

1 more.

codeinterpreter-api by shroominic

Starred by

Tim Suchanek(Founder of expand.ai),

Jonathan Ragan-Kelley(Professor at MIT), and

1 more.

gpt-code-ui by ricklamers

Open source implementation of OpenAI's ChatGPT Code interpreter

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai), and

16 more.

TinyLlama by jzhang38

Tiny pretraining project for a 1.1B Llama model

Starred by

Vincent Weisser(Cofounder of Prime Intellect),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

3 more.

yarn by jquesnelle

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

Starred by

Simon Willison(Author of Django),

Jeff Hammerbacher(Cofounder of Cloudera), and

3 more.

OpenMoE by XueFuzhao

Open-source MoE LLM for research

Starred by

Elvis Saravia(Founder of DAIR.AI),

Vincent Weisser(Cofounder of Prime Intellect), and

8 more.

AgentBench by THUDM

Benchmark for evaluating LLMs as agents across diverse environments

LLM fine-tuning and evaluation platform

Starred by

Jared Palmer(Ex-VP AI at Vercel; Founder of Turborepo; Author of Formik, TSDX) and

Vincent Weisser(Cofounder of Prime Intellect).

haven by redotvideo

346

Starred by

Wing Lian(Founder of Axolotl AI),

Omar Sanseviero(DevRel at Google DeepMind), and

4 more.

metal-flash-attention by philipturner

Metal port of FlashAttention for Apple silicon

517

updated 10 months ago

Starred by

Lilian Weng(Cofounder of Thinking Machines Lab),

Anton Osika(Cofounder of Lovable), and

15 more.

gpt-engineer by AntonOsika

CLI platform for code generation experimentation

55k

Fast, memory-efficient attention implementation

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Jiayi Pan(Author of SWE-Gym; MTS at xAI), and

25 more.

flash-attention by Dao-AILab

0.7%

19k

updated 22 hours ago

Starred by

Vincent Weisser(Cofounder of Prime Intellect) and

Ying Sheng(Author of SGLang).

ringattention by haoliuhl

Jax implementation of RingAttention for large context models (research paper)

724

Starred by

Tobi Lutke(Cofounder of Shopify),

Omar Sanseviero(DevRel at Google DeepMind), and

19 more.

mlc-llm by mlc-ai

Universal LLM deployment engine with ML compilation

21k

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Vincent Weisser(Cofounder of Prime Intellect), and

17 more.

StableLM by Stability-AI

Language models by Stability AI

Starred by

Chenlin Meng(Cofounder of Pika) and

Anastasios Angelopoulos(Cofounder of LMArena).

so-vits-svc by svc-develop-team

Singing voice conversion using SoftVC VITS

28k

Starred by

Tobi Lutke(Cofounder of Shopify),

Anton Osika(Cofounder of Lovable), and

14 more.

openplayground by nat

LLM playground for local laptop use

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Shawn Wang(Editor of Latent Space), and

9 more.

llm by rustformers

Rust ecosystem for LLM Rust inference (unmaintained)

Cleaned dataset for Alpaca LLM training

Starred by

Tobi Lutke(Cofounder of Shopify),

Omar Sanseviero(DevRel at Google DeepMind), and

5 more.

AlpacaDataCleaned by gururise

C/C++ library for local LLM inference

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Nat Friedman(Former CEO of GitHub), and

40 more.

llama.cpp by ggml-org

0.7%

85k

updated 20 hours ago

Starred by

Nat Friedman(Former CEO of GitHub),

Jason Miller(Author of Preact), and

18 more.

chatgpt-retrieval-plugin by openai

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

21k

Starred by

Anastasios Angelopoulos(Cofounder of LMArena),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

26 more.

evals by openai

Framework for evaluating LLMs and LLM systems, plus benchmark registry

17k

updated 8 months ago

Starred by

Anton Osika(Cofounder of Lovable),

Wing Lian(Founder of Axolotl AI), and

12 more.

OpenChatKit by togethercomputer

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

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Jonathan Ragan-Kelley(Professor at MIT), and

18 more.

FlexLLMGen by FMInference

High-throughput generation engine for LLMs with limited GPU memory

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Carol Willing(Core Contributor to CPython, Jupyter), and

54 more.

langchain by langchain-ai

Framework for building LLM-powered applications

114k

Starred by

Travis Fischer(Founder of Agentic),

Shizhe Diao(Research Scientist at NVIDIA; Author of LMFlow), and

4 more.

ChatGPT by acheong08

Reverse-engineered API for ChatGPT, plus official OpenAI API support

28k

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Daniel Gross(Cofounder of Safe Superintelligence), and

23 more.

RWKV-LM by BlinkDL

RNN for LLM, transformer-level performance, parallelizable training

14k

updated 4 days ago

Starred by

Tobi Lutke(Cofounder of Shopify),

Daniel Gross(Cofounder of Safe Superintelligence), and

32 more.

nanoGPT by karpathy

Minimalist repo for training/finetuning GPT models

44k

updated 8 months ago

Starred by

Yaowei Zheng(Author of LLaMA-Factory),

Travis Fischer(Founder of Agentic), and

3 more.

self-instruct by yizhongw

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

Starred by

Kent Dodds(Cofounder of Remix),

Alejandro Matamala Ortiz(Cofounder of Runway), and

6 more.

agentic by transitive-bullshit

AI agent stdlib for LLM-based TypeScript tooling

18k

Code exploration tool for GitHub Copilot's client-side codebase

updated 5 days ago

Starred by

Jeff Hammerbacher(Cofounder of Cloudera).

copilot-explorer by thakkarparth007

688

Starred by

Beyang Liu(Cofounder of Sourcegraph).

chatgpt-vscode by mpociot

VS Code extension for interacting with ChatGPT

ChatGPT fine-tune for primary care medicine

medical-chatgpt by lucidrains

315

Starred by

Shizhe Diao(Research Scientist at NVIDIA; Author of LMFlow),

Vincent Weisser(Cofounder of Prime Intellect), and

5 more.

galai by paperswithcode

Scientific language model API

Starred by

Nat Friedman(Former CEO of GitHub),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

13 more.

trlx by CarperAI

Distributed RLHF for LLMs

Starred by

Boris Cherny(Creator of Claude Code; MTS at Anthropic),

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), and

29 more.

whisper by openai

Speech recognition model for multilingual transcription/translation

87k

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Simon Willison(Author of Django), and

7 more.

LAVIS by salesforce

Library for language-vision AI research

11k

Starred by

Tim J. Baek(Founder of Open WebUI),

Daniel Han(Cofounder of Unsloth), and

18 more.

bitsandbytes by bitsandbytes-foundation

PyTorch library for k-bit quantization, enabling accessible LLMs

Course reading list for large language models

Starred by

Ying Sheng(Author of SGLang) and

Jeff Hammerbacher(Cofounder of Cloudera).

llm-seminar by craffel

311

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Jiayi Pan(Author of SWE-Gym; MTS at xAI), and

13 more.

alpa by alpa-projects

Auto-parallelization framework for large-scale neural network training and serving

Pretrained DALL-E 2 model from LAION

dalle2-laion by LAION-AI

503

Starred by

Buck Shlegeris(Cofounder of Redwood Research),

Shizhe Diao(Research Scientist at NVIDIA; Author of LMFlow), and

1 more.

YaLM-100B by yandex

GPT-like neural network for text generation/processing

Starred by

Anastasis Germanidis(Cofounder of Runway) and

Jiayi Pan(Author of SWE-Gym; MTS at xAI).

Video-Pre-Training by openai

Minecraft agent learning via video pretraining research paper

Starred by

George Hotz(Author of tinygrad; Founder of the tiny corp, comma.ai),

Anton Bukov(Cofounder of 1inch Network), and

19 more.

tinygrad by tinygrad

Minimalist deep learning framework for education and exploration

30k

Starred by

Omar Sanseviero(DevRel at Google DeepMind),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

2 more.

CogVideo by zai-org

Text-to-video generation models (CogVideoX, CogVideo)

Starred by

Vincent Weisser(Cofounder of Prime Intellect),

Tim J. Baek(Founder of Open WebUI), and

23 more.

trl by huggingface

0.7%

Library for transformer RL

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Jeff Hammerbacher(Cofounder of Cloudera), and

7 more.

x-transformers by lucidrains

Transformer library with extensive experimental features

updated 3 days ago

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

David Ha(Cofounder of Sakana AI), and

9 more.

dalle-mini by borisdayma

Text-to-image model for generating images from text prompts

Code LLM guide for using pre-trained large language models of source code

Starred by

Andreas Jansson(Cofounder of Replicate).

Code-LMs by VHellendoorn

apps by hendrycks

Dataset for measuring coding challenge competence (NeurIPS 2021)

480

GPT models for semantic search, code, and pretrained models

Starred by

Philipp Schmid(DevRel at Google DeepMind),

Omar Sanseviero(DevRel at Google DeepMind), and

3 more.

sgpt by Muennighoff

870

Starred by

Nat Friedman(Former CEO of GitHub),

Yaowei Zheng(Author of LLaMA-Factory), and

8 more.

CodeGen by salesforce

Open-source model family for program synthesis

Starred by

Ying Sheng(Author of SGLang),

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and

6 more.

adapters by adapter-hub

Unified library for parameter-efficient transfer learning in NLP

Starred by

Amanpreet Singh(Cofounder of Contextual AI),

Jeff Hammerbacher(Cofounder of Cloudera), and

1 more.

Megatron-DeepSpeed by bigscience-workshop

Transformer LM research repo for BERT & GPT-2 training at scale

Multimodal model for augmenting generative language models

Starred by

Jesse Clark(Cofounder of Marqo),

Vincent Weisser(Cofounder of Prime Intellect), and

2 more.

magma by Aleph-Alpha-Research

489

Starred by

Jeff Hammerbacher(Cofounder of Cloudera),

Stas Bekman(Author of "Machine Learning Engineering Open Book"; Research Engineer at Snowflake), and

16 more.

gpt-neox by EleutherAI

Framework for training large-scale autoregressive language models

Starred by

Sebastian Raschka(Author of "Build a Large Language Model (From Scratch)"),

Jiayi Pan(Author of SWE-Gym; MTS at xAI), and

2 more.

pytorch-grad-cam by jacobgil

PyTorch SDK for explainable AI in computer vision

updated 4 months ago

Starred by

Sourabh Bajaj(Cofounder of Uplimit),

Jeff Hammerbacher(Cofounder of Cloudera), and

3 more.

annotated_deep_learning_paper_implementations by labmlai

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

63k

updated 4 days ago

Starred by

Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n),

Phil Wang(Prolific Research Paper Implementer), and

10 more.

vit-pytorch by lucidrains

PyTorch library for Vision Transformer variants and related techniques

24k

Starred by

Junyang Lin(Core Maintainer of Alibaba Qwen),

Collin Burns(MTS at Anthropic; Author of MMLU), and

1 more.

PromptPapers by thunlp

Paper list for prompt-based tuning of pre-trained language models

Starred by

Shengjia Zhao(Chief Scientist at Meta Superintelligence Lab),

Patrick von Platen(Research Engineer at Mistral; Author of Hugging Face Diffusers), and

4 more.

glide-text2im by openai

Text-conditional image synthesis model from research paper

Starred by

Aravind Srinivas(Cofounder of Perplexity),

Nat Friedman(Former CEO of GitHub), and

26 more.

minGPT by karpathy

Minimal PyTorch re-implementation for GPT training and inference

22k

PyTorch for text-to-image generation research

Starred by

Chenlin Meng(Cofounder of Pika) and

Robin Rombach(Cofounder of Black Forest Labs).

mindall-e by kakaobrain

636

updated 3 years ago

Starred by

Lewis Tunstall(Research Engineer at Hugging Face),

Omar Sanseviero(DevRel at Google DeepMind), and

1 more.

Transformers-Recipe by dair-ai

Study guide for learning about Transformers

Starred by

Aravind Srinivas(Cofounder of Perplexity),

Zhuohan Li(Author of vLLM), and

16 more.

lm-evaluation-harness by EleutherAI

Framework for few-shot language model evaluation

10k

updated 22 hours ago

Starred by

Clement Delangue(Cofounder of Hugging Face),

Syrus Akbary(Founder of Wasmer), and

19 more.

tokenizers by huggingface

Fast tokenizer library optimized for research and production

10k

Starred by

Elvis Saravia(Founder of DAIR.AI),

Woosuk Kwon(Author of vLLM), and

5 more.

DeepLearningExamples by NVIDIA

Deep learning examples for training and deployment

14k

created 7 years ago

Starred by

Albert Gu(Cofounder of Cartesia; Professor at CMU),

Elvis Saravia(Founder of DAIR.AI), and

22 more.

pytorch-lightning by Lightning-AI

Deep learning framework for pretraining, finetuning, and deploying AI models

30k

updated 19 hours ago

Starred by

Aravind Srinivas(Cofounder of Perplexity),

Wing Lian(Founder of Axolotl AI), and

27 more.

DeepSpeed by deepspeedai

Deep learning optimization library for distributed training and inference

40k

updated 21 hours ago

Starred by

Aravind Srinivas(Cofounder of Perplexity),

François Chollet(Cofounder of Ndea, ARC Prize; Author of Keras), and

15 more.

horovod by horovod

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

Starred by

Georgios Konstantopoulos(CTO, General Partner at Paradigm),

Chaoyu Yang(Founder of Bento), and

11 more.

mesh-transformer-jax by kingoflolz

JAX library for model-parallel transformers

GPT-3 prompt testing and experimentation

Starred by

Taranjeet Singh(Cofounder of Mem0).

gpt-3-experiments by minimaxir

699

JS library for GPT-2/GPT-3 text tokenization

updated 5 years ago

Starred by

Simon Willison(Author of Django),

Jared Palmer(Ex-VP AI at Vercel; Founder of Turborepo; Author of Formik, TSDX), and

1 more.

GPT-3-Encoder by latitudegames

720

Tiny client for the OpenAI API

Starred by

Mckay Wrigley(Founder of Takeoff AI).

openai-api by njerschow

282

Machine-learning-for-proteins by yangkky

ML papers for protein applications

Starred by

Vincent Weisser(Cofounder of Prime Intellect) and

Elvis Saravia(Founder of DAIR.AI).

deeplearning-biology by hussius

Deep learning implementations in biology

created 9 years ago

Starred by

Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"),

Thomas Wolf(Cofounder of Hugging Face), and

1 more.

stable-baselines3 by DLR-RM

PyTorch library for reinforcement learning algorithm implementations

11k

Curated list of annotated research papers

Starred by

Elvis Saravia(Founder of DAIR.AI) and

Omar Sanseviero(DevRel at Google DeepMind).

annotated_research_papers by AakashKumarNain

Starred by

Aravind Srinivas(Cofounder of Perplexity),

Lilian Weng(Cofounder of Thinking Machines Lab), and

20 more.

baselines by openai

RL algorithm implementations for research

Starred by

Aravind Srinivas(Cofounder of Perplexity),

Taranjeet Singh(Cofounder of Mem0), and

1 more.

awesome-gpt3 by elyase

GPT-3 demos and articles collection

Starred by

Lilian Weng(Cofounder of Thinking Machines Lab),

Aravind Srinivas(Cofounder of Perplexity), and

19 more.

tensor2tensor by tensorflow

Deprecated library for deep learning models/datasets, successor to Trax

Starred by

Elie Bursztein(Cybersecurity Lead at Google DeepMind),

Omar Khattab(Author of DSPy, ColBERT; Professor at MIT), and

11 more.

gpt-neo by EleutherAI

GPT-2/3-style model implementation using mesh-tensorflow

updated 3 years ago

Starred by

Phil Wang(Prolific Research Paper Implementer),

Jane Manchun Wong(Security Researcher; Tech Blogger), and

1 more.

deep-daze by lucidrains

CLI tool for text-to-image generation using CLIP and SIREN

updated 3 years ago

Starred by

Clement Delangue(Cofounder of Hugging Face),

Lilian Weng(Cofounder of Thinking Machines Lab), and

70 more.

transformers by huggingface

ML library for pretrained model inference and training

148k

Starred by

Wing Lian(Founder of Axolotl AI),

Chenlin Meng(Cofounder of Pika), and

11 more.

serve by jina-ai

Framework for building cloud-native multimodal AI apps

22k

updated 4 months ago

Starred by

Boris Cherny(Creator of Claude Code; MTS at Anthropic),

Travis Fischer(Founder of Agentic), and

12 more.

prophet by facebook

Forecasting tool for time series data

20k

Curated list of GPT-3 tools, libraries, and resources

awesome-gpt3 by mikhail-bot

318

WWDC session notes for quick reference

WWDC by Blackjacx