AlbertBJ's repositories
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
awesome-chatgpt-prompts
This repo includes ChatGPT prompt curation to use ChatGPT better.
cake
Distributed LLM inference for mobile, desktop and server.
chatarena
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
exo
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
FlagEmbedding
Dense Retrieval and Retrieval-augmented LLMs
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
llm-awq
[MLSys 2024] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
megalodon
Reference implementation of Megalodon 7B model
mem0
The memory layer for Personalized AI
milvus
A cloud-native vector database, storage for next generation AI applications
MiniGemini
Official implementation for Mini-Gemini
MobiLlama
MobiLlama : Small Language Model tailored for edge devices
momask-codes
Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions"
mPLUG-DocOwl
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
nlp-hanzi-similar
The hanzi similar tool.(汉字相似度计算工具，中文形近字算法。可用于手写汉字识别纠正，文本混淆等。)
ollama
Get up and running with Llama 3, Mistral, Gemma, and other large language models.
openai-cookbook
Examples and guides for using the OpenAI API
orpo
Official repository for ORPO
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
python-pinyin
汉字转拼音(pypinyin)
Qwen-VL
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
self-rewarding-lm-pytorch
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI
swift
ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs
unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory