kunato

kunato's Stars

• mlc-ai/mlc-llm

  Universal LLM Deployment Engine with ML Compilation

  Language:Python19.2k1741.4k1.6k

• princeton-nlp/SWE-agent

  [NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.

  Language:Python13.7k973861.4k

• stanford-oval/storm

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

  Language:Python13.4k981401.2k

• nilsherzig/LLocalSearch

  LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

  Language:Go5.7k2996362

• InternLM/lmdeploy

  LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

  Language:Python4.7k381.5k428

• Zejun-Yang/AniPortrait

  AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

  Language:Python4.7k61187582

• mishushakov/llm-scraper

  Turn any webpage into structured data using LLMs

  Language:TypeScript2.4k1827146

• facebookresearch/schedule_free

  Schedule-Free Optimization in PyTorch

  Language:Python1.9k153265

• chenxwh/insanely-fast-whisper

  Incredibly fast Whisper-large-v3

  Language:Jupyter Notebook1.8k130103

• McGill-NLP/llm2vec

  Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

  Language:Python1.3k2211995

• PKU-YuanGroup/MagicTime

  MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

  Language:Python1.3k2129125

• RLHFlow/RLHF-Reward-Modeling

  Recipes to train reward model for RLHF.

  Language:Python901203171

• huggingface/lighteval

  Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

  Language:Python8113014397

• facebookresearch/generative-recommenders

  Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

  Language:Python7622351143

• xfactlab/orpo

  Official repository for ORPO

  Language:Python42162739

• ContinualAI/colab

  Continual Learning tutorials and demo running on Google Colaboratory.

  Language:Jupyter Notebook345264102

• Ledzy/BAdam

  [NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models

  Language:Python21441313

• lm-sys/arena-hard

  Arena-Hard benchmark

  Language:Jupyter Notebook20071411

• arcee-ai/PruneMe

  Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

  Language:Python19631226

• npuichigo/openai_trtllm

  OpenAI compatible API for TensorRT LLM triton backend

  Language:Rust17782227

• NVIDIA/trt-llm-as-openai-windows

  This reference can be used with any existing OpenAI integrated apps to run with TRT-LLM inference locally on GeForce GPU on Windows instead of cloud.

  Language:Python1165112

• asappresearch/simple-tts

  Contains the code associated with the ICLR submission for our text-to-speech diffusion model

  Language:Python50422

• amirarsalan90/promptrefiner

  Language:Jupyter Notebook49314

• declare-lab/resta

  Restore safety in fine-tuned language models through task arithmetic

  Language:Python26211

• AlignInc/aligner-replication

  The reproduct of the paper - Aligner: Achieving Efficient Alignment through Weak-to-Strong Correction

  Language:Python2100

• ex3ndr/supervoice-dataset

  60k hours of phoneme-aligned audio from audio books

  Language:Python16301

• Aratako/Task-Vector-Merge-Optimzier

  Language:Python14100

• MeNicefellow/Mixtral-Expert-Trimmer

  Language:Python9101

• argilla-io/distilabel-workbench

  A working repository for experimental pipelines in distilabel

  Language:Jupyter Notebook7401

• josejg/instruction_following_eval

  Instruction Following Eval

  Language:Python42