plutoyuxie

langchain

🦜🔗 Build context-aware reasoning applications

ollama

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

fastapi

FastAPI framework, high performance, easy to learn, fast to code, ready for production

stable-diffusion

A latent text-to-image diffusion model

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

LLaMA-Factory

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

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

milvus

A cloud-native vector database, storage for next generation AI applications

albumentations

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

weaviate

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

cs231n.github.io

Public facing notes page

instructor

structured outputs for llms

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

taming-transformers

Taming Transformers for High-Resolution Image Synthesis

eat_pytorch_in_20_days

Pytorch🍊🍉 is delicious, just eat it! 😋😋

PerceptualSimilarity

LPIPS metric. pip install lpips

NExT-GPT

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

infinity

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

rag-from-scratch

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

cs231n

cs231n assignments sovled by https://ghli.org

NL2SQL

Text2SQL 语义解析数据集、解决方案、paper资源整合项目

TinyLLaVA_Factory

A Framework of Small-scale Large Multimodal Models

TCD

Official Repository of the paper "Trajectory Consistency Distillation"

LLM-Finetune

大语言模型微调，Qwen2、GLM4指令微调

llm_notebooks

AI 应用示例合集