sandkoan

sandkoan's Stars

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda24.8k2501412.8k

• naklecha/llama3-from-scratch

  llama3 implementation one matrix multiplication at a time

  Language:Jupyter Notebook13.9k98181.1k

• stanford-oval/storm

  An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

  Language:Python13.7k991521.3k

• marimo-team/marimo

  A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

  Language:Python8.6k44881315

• mistralai/mistral-finetune

  Language:Python2.8k4039239

• nus-apr/auto-code-rover

  A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.

  Language:Python2.8k2949295

• mlabonne/llm-datasets

  High-quality datasets, tools, and concepts for LLM fine-tuning.

  2.1k351186

• RManLuo/Awesome-LLM-KG

  Awesome papers about unifying LLMs and KGs

  2.1k1131159

• EleutherAI/math-lm

  Language:Python1.1k184885

• SafeAILab/EAGLE

  Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)

  Language:Python8641314691

• open-compass/MixtralKit

  A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

  Language:Python76581681

• mirage-project/mirage

  Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA

  Language:C++683145339

• facebookresearch/searchformer

  Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".

  Language:Jupyter Notebook3385118

• jondurbin/bagel

  A bagel, with everything.

  Language:Python314111231

• virattt/financial-datasets

  Financial datasets for LLMs 🧪

  Language:Python2568235

• isi-nlp/Zoph_RNN

  C++/CUDA toolkit for training sequence and sequence-to-sequence models across multiple GPUs

  Language:C++186441265

• HITsz-TMG/awesome-llm-attributions

  A Survey of Attributions for Large Language Models

  174548

• Vance0124/Token-level-Direct-Preference-Optimization

  Reference implementation for Token-level Direct Preference Optimization(TDPO)

  Language:Python1191713

• logix-project/logix

  AI Logging for Interpretability and Explainability🔬

  Language:Python939287

• walkerdb/supreme_court_transcripts

  Language:Python716518

• Max-Fu/tvl

  Language:Python63264

• nateraw/audiocraft

  Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

  Language:Python54324

• google-deepmind/pix2act

  Language:Python521009

• foobarbaz-inc/conversation-memory-streamlit

  Demo of ConversationEntityMemory in Streamlit.

  Language:Python51116

• vroomai/live

  🎧 Chat with Ableton Live in your browser.

  Language:JavaScript28102

• cognitivecomputations/agenticworker

  Language:Python23202

• kozistr/triton-grpc-proxy-rs

  Proxy server for triton gRPC server that inferences embedding model in Rust

  Language:Rust20202

• symbolica-ai/gap-sys

  Rust bindings to GAP (Groups, Algorithms, Programming)

  Language:Rust18302

• talaviram/OpenSpoken

  Real-Time Transcription for Apple Devices using Apple’s Speech Recognition

  Language:Swift17212

• neefrehman/millzbot

  A GPT-2 bot trained on my bosses tweets, and a guide to making your own

  Language:Python15207