GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
- image2text
- video-understanding
- vlm
- reasoning
111,820 visible repositories in the index
2,233–2,256 of 7,821 · Most stars
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
A linux system information web dashboard using psutils and flask
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Deep Learning toolkit for Computer Vision.
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
SQLAlchemy database migrations for Flask applications using Alembic
A modular RL library to fine-tune language models to human preferences
A library for converting HTML into PDFs using ReportLab
Node based visual scripting system designed for motion graphics in Blender.
Kubernetes shell: An integrated shell for working with the Kubernetes
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/
Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis
Source code for the book "Black Hat Python" by Justin Seitz. The code has been fully converted to Python 3, reformatted to comply with PEP8 standards and refactored to eliminate dependency issues involving the implementation of deprecated libraries.
Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
Meld for macOS
Intelligent Music & Video Automation Platform
Starter code for working with the YouTube-8M dataset.
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.
Implements harmful/harmless refusal removal using pure HF Transformers
A jquery-like library for python
A fork and successor of the Sulley Fuzzing Framework
Deep Eye orchestrates multiple AI providers (OpenAI, Claude, Grok, Gemini, OLLAMA, Groq, Mistral, OpenRouter, LiteLLM, LM Studio) for intelligent payload generation, scans targets for 45+ vulnerability types, and produces professional reports with compliance mapping.