Lyngsoe

Lyngsoe's Stars

• duriantaco/pykomodo

  A Python-based parallel file chunking system designed for processing large codebases into LLM-friendly chunks.

  Language:Python21

• noamgat/lm-format-enforcer

  Enforce the output format (JSON Schema, Regex etc) of a language model

  Language:Python1.7k76

• aphrodite-engine/aphrodite-engine

  Large-scale LLM inference engine

  Language:C++1.3k149

• axolotl-ai-cloud/axolotl

  Go ahead and axolotl questions

  Language:Python8.9k978

• huggingface/peft

  🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

  Language:Python17.8k1.8k

• hiyouga/LLaMA-Factory

  Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

  Language:Python44.6k5.5k

• guidance-ai/guidance

  A guidance language for controlling large language models.

  Language:Jupyter Notebook19.9k1.1k

• JoakimEdin/medical-coding-reproducibility

  Language:Jupyter Notebook7827

• S-LoRA/S-LoRA

  S-LoRA: Serving Thousands of Concurrent LoRA Adapters

  Language:Python1.8k106

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python41.9k6.3k

• tiantiantu/KSI

  This repository contains codes for Knowledge Source Intergration (KSI) framework

  Language:Python79

• MahmoudAshraf97/whisper-diarization

  Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

  Language:Jupyter Notebook4.3k389

• ggerganov/whisper.cpp

  Port of OpenAI's Whisper model in C/C++

  Language:C++38.6k4k

• OpenNMT/CTranslate2

  Fast inference engine for Transformer models

  Language:C++3.7k338

• m-bain/whisperX

  WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

  Language:Python14.5k1.6k

• VodLM/vod

  End-to-end training of Retrieval-Augmented LMs (REALM, RAG)

  Language:Python223

• josStorer/RWKV-Runner

  A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.

  Language:TypeScript5.7k542

• huggingface/text-generation-inference

  Large Language Model Text Generation Inference

  Language:Python9.9k1.2k

• python-poetry/install.python-poetry.org

  The official Poetry installation script

  Language:Python22555

• neuralmagic/deepsparse

  Sparsity-aware deep learning inference runtime for CPUs

  Language:Python3.1k181

• stanfordnlp/dspy

  DSPy: The framework for programming—not prompting—language models

  Language:Python22.5k1.7k

• ml6team/fondant

  Production-ready data processing made easy and shareable

  Language:Python34926

• BlinkDL/SmallInitEmb

  LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence

  Language:Python604

• deepspeedai/DeepSpeed

  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

  Language:Python37.5k4.3k

• BlinkDL/RWKV-LM

  RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

  Language:Python13.4k900

• python-poetry/poetry

  Python packaging and dependency management made easy

  Language:Python32.8k2.3k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python16.4k1.5k

• NVIDIA/FasterTransformer

  Transformer related optimization, including BERT, GPT

  Language:C++6.1k901

• qdrant/qdrant

  Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

  Language:Rust22.6k1.5k

• eugeneyan/open-llms

  📋 A list of open LLMs available for commercial use.

  11.8k818