hiyouga

developer-roadmap

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

generative-ai-for-beginners

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

llm-course

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

chroma

the AI-native open-source embedding database

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

mamba

Mamba SSM architecture

ML-Papers-of-the-Week

🔥Highlighting the top ML papers every week.

ML-Papers-Explained

Explanation to key concepts in ML

gpt-fast

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

clip-interrogator

Image to prompt with BLIP and CLIP

Qwen-Agent

Agent framework and applications built upon Qwen1.5 & Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

Data-Copilot

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

DeepSeek-LLM

DeepSeek LLM: Let there be answers

pymilvus

Python SDK for Milvus.

Yuan-2.0

Yuan 2.0 Large Language Model

tensor_parallel

Automatically split your PyTorch models on multiple GPUs for training & inference

gpt_paper_assistant

GPT4 based personalized ArXiv paper assistant bot

H2O

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

llm-inference-benchmark

LLM Inference benchmark

URIAL

unicom

universal visual model trained on LAION-400M

LoftQ

text2image_safety

factoid-wiki

Dense X Retrieval: What Retrieval Granularity Should We Use?

Efficient-LLM-Survey

The Efficiency Spectrum of LLM

enhance_long

This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without training, and can be used directly in the LLM inference phase.

chain-of-thought

Research papers about Chain of Thought (CoT)

Blue-arXiv-Theme

Blue theme for arXiv website