3 dépôts
Utilities for transforming model weights into optimized formats for specific inference runtimes.
Distinct from Model Inference Optimizations: Distinct from Model Inference Optimizations: focuses on the transformation pipeline rather than the optimization techniques themselves.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Model Conversion Tools. Refine with filters or upvote what's useful.
ChatGLM3 is a comprehensive framework for deploying, fine-tuning, and serving large language models. It functions as a high-performance inference engine designed to support conversational AI, enabling developers to build interactive agents capable of multi-turn dialogue, autonomous code execution, and structured tool invocation. The project distinguishes itself through its focus on hardware-agnostic deployment and resource optimization. It supports distributed model parallelism across multiple graphics cards, paged key-value caching for concurrent request processing, and weight quantization t
Transforms standard language models into optimized intermediate representations to improve execution speed and reduce memory usage.
OpenChatKit is a training and inference toolkit for large language models. It provides a comprehensive set of tools for managing the model lifecycle, including a fine-tuning pipeline, a model weight converter, and a command-line interface for interacting with conversational agents. The toolkit features a framework for retrieval augmented generation, allowing models to incorporate relevant context from external vector indices. It also includes utilities for converting trained model checkpoints into formats compatible with standard inference libraries. The project covers conversational AI trai
Includes utilities for transforming trained model checkpoints into formats compatible with standard inference libraries.
This project is a deep learning implementation of the RetinaNet architecture for detecting and classifying objects within images. Built as a Keras object detection framework and a TensorFlow computer vision tool, it provides a complete neural network implementation based on the RetinaNet paper. The framework includes specialized components such as a Feature Pyramid Network and a focal loss function to handle object detection. It features a configurable backbone architecture and anchor-based bounding boxes to predict object locations across varying scales and aspect ratios. The toolset covers
Transforms trained regression and classification networks into optimized formats suitable for object detection inference.