sijingfeng88

web_rag

Oobabooga Text-Gen Web UI extension: get web content, add to context

text-generation-webui-extensions

graph-rag

Graph based retrieval + GenAI = Better RAG in production

Flowise

Drag & drop UI to build your customized LLM flow

RAGArch

RAGArch is a Streamlit-based application that empowers users to experiment with various components and parameters of Retrieval-Augmented Generation (RAG) pipelines. Utilizing the power of Llamaindex, RAGArch facilitates the testing of different configurations to see how they perform.

grok-1

Grok open release

stable-diffusion-webui

Stable Diffusion web UI

stable-diffusion-webui

Stable Diffusion web UI

text-generation-webui

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

Anima

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

UMLS-MetaMap-API-Scripts

This repository is dedicated to development of Python scripts which use API to UMLS MetaMap to map semantics of common data elemnts to UMLS and NCI concepts

clinical_informatics_umls

An exploratory, tutorial and analytical view of the Unified Medical Language System (UMLS) & the software/technologies provided via being a free UMLS license holder. This repo will subset 2021AB UMLS native release, introduce/build upon UMLS provided tools to load a configured subset into first a relational database --> MySQL, SQLite, PostgreSQL and MariaDB all covered within this repo. Next the UMLS subset which is stored in a relational DB will be queried, modeled and lastly loaded into a defined Neo4j label property graph. Lastly, Neo4j database containing UMLS 2021AB subset in schema promoting intuitive analysis and rich visualization will become the central datastore for analysis. The datastore contains ~5 million distinct nodes & >40 million distinct relationships (edges). Currently, Neo4j is running via Docker but deployment options are NOT limited to Docker. If choosing to deploy via Neo4j Aura, server, Neo4j Desktop, VM etc... Please note and be aware of the specific volumes and environment variables specified within this repository (docker run). The ability for the loaded Neo4j Graph to interact with RDF data (i.e. import/export RDF data to and from Neo4j) may not be possible via all Neo4j deployment avenues (i.e. Neo4j Aura currently does not support RDF integration that is demonstrated in this repository).

data-dictionary-cui-mapping

This repository aims to speed up the process of querying and assigning relevant UMLS CUIs to fields in your data dictionary. Currently, you can customize batch query scripts that utilize the UMLS api, MetaMap api, and/or an experimental semantic search approach with vector embeddings. Further development in progress.

getUMLS

Rpackage to query the UMLS metathesaurus

nomogram

Python tools for constructing nomograms based on logistic regression model

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

AI-Deep-Learning-Lab-2023

generative_inpainting

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

deepfillv2-pytorch

A PyTorch reimplementation of the paper Free-Form Image Inpainting with Gated Convolution (DeepFill v2) (https://arxiv.org/abs/1806.03589)

machine-learning

Repository for activities of the machine learning committee

mindspore

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

InternGPT

InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)

llama_index

LlamaIndex is a data framework for your LLM applications

codellama

Inference code for CodeLlama models

examples

Jupyter Notebooks to help you get hands-on with Pinecone vector databases

h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/

openmarkov_cloud

Openmarkov Web Application

kohya_ss

LLaMA-LoRA-Tuner

UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.