luome

mistral-inference

Official inference library for Mistral models

grok-1

Grok open release

flash-attention-minimal

Flash Attention in ~100 lines of CUDA (forward pass only)

algebraic-nnhw

Deep learning accelerator architectures requiring half the multipliers

peft

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

jsonformer

A Bulletproof Way to Generate Structured JSON from Language Models

outlines

Structured Text Generation

induced-rationales-markup-tokens

Paper reproduction code: Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models

knnlm

LWM

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Bert-VITS2

vits2 backbone with multilingual-bert

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

chroma

the AI-native open-source embedding database

litellm

Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

ml-ferret

GPTs

leaked prompts of GPTs

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

llama.cpp

LLM inference in C/C++

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

aimoneyhunter

ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English version for more insights.

llm-inference-benchmark

LLM Inference benchmark

RRHF

[NIPS2023] RRHF & Wombat

lobe-chat

🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Bedrock / Azure / Mistral / DeepSeek),Knowledge Base(file upload / knowledge management / RAG ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT/ Claude application.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

mlx-examples

Examples in the MLX framework

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.