tricktreat

ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

openai-translator

基于 ChatGPT API 的划词翻译浏览器插件和跨平台桌面端应用 - Browser extension and cross-platform desktop application for translation based on ChatGPT API.

mamba

Mamba SSM architecture

outlines

Structured Text Generation

AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

alphageometry

Vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

ReplaceAnything

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

dreamoving-project

Official implementation of DreaMoving

MOSS-RLHF

MOSS-RLHF

LookaheadDecoding

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

GPT-4V-Act

AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI

nanotron

Minimalistic large language model 3D-parallelism training

llm-reasoners

A library for advanced large language model reasoning

mamba.py

A simple and efficient Mamba implementation in PyTorch and MLX.

write-you-a-vector-db

A Vector Database Tutorial (over CMU-DB's BusTub system)

LanguageAgentTreeSearch

Official repository for ICML'24 paper "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"

vstar

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"

assistants

The ⭐️ Open Source Assistants API allows you to build AI assistants within your own applications with your own models. 100% private, 75% Cheaper & 23x Faster Assistants. Same API/SDK. Written in Rust

energy-data

Data on energy by Our World in Data

SpeculativeDecodingPapers

📰 Must-read papers and blogs on Speculative Decoding ⚡️

doc-story-generation

Imbalance-VLM

moe_attention

Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"

EasyKV

Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)

APO

Code for ACL2024 paper - Adversarial Preference Optimization (APO).

GenDeF