This repository contains demos I made with the Transformers library by HuggingFace.

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

NVIDIA curated collection of educational resources related to general purpose GPU programming.

Hackable CLI tool for converting Markdown files to PDF using Node.js and headless Chrome.

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On

pytorch-profiler

Profiling and inspecting memory in pytorch

🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.

PyTorch layer-by-layer model profiler

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, LoRA

Real time video and audio processing examples with Streamlit and streamlit-webrtc

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Implementation of Nougat Neural Optical Understanding for Academic Documents

Improved file parsing for LLM’s

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Using GPT to parse PDF

Parse files for optimal RAG

GPT4V-level open-source multi-modal model based on Llama3-8B

a state-of-the-art-level open visual language model | 多模态预训练模型

AgentTuning: Enabling Generalized Agent Abilities for LLMs

A collective list of free APIs

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a mu…

[ACL 2024] AUTOACT: Automatic Agent Learning from Scratch for QA via Self-Planning

An LLM-based Web Navigating Agent (KDD'24)