Projects sharing features with BLIP

InternVL is a vision-language model framework that fuses a visual encoder with a large language model to translate image features into textual tokens for reasoning. It provides a system for multimodal inference and dialogue, enabling the processing of images and text to answer questions or generate descriptions. The project is distinguished by its high-resolution image processing, which uses dynamic tiling to maintain detail for images up to 4K resolution, and its chain-of-thought visual reasoning for solving complex mathematical and spatial problems. It also supports temporal frame sampling

nanoVLM is a training framework and toolkit for small vision-language models. It provides a PyTorch-based environment for training and fine-tuning models to associate image inputs with textual descriptions and generate natural language answers. The project includes a cloud model versioning tool for saving and loading model weights to centralized repositories to synchronize assets across environments. It also features a dedicated evaluation suite for measuring the accuracy and reliability of vision-language models against standard task datasets. The framework covers GPU resource planning thro

Clip-as-service is a deployable framework for generating multi-modal embeddings and executing neural searches. It provides a vector embedding server and a CLIP embedding API to convert images and text into shared vector representations via network interfaces. The system functions as a multi-modal ranking system and neural search engine, enabling the retrieval of images through text queries or the identification of matching text descriptions for images. It also includes a visual reasoning service used to analyze images and verify object presence, counts, and colors by comparing visual data aga

ImageBind is a multi-modal embedding model and joint representation learner that maps images, text, audio, and other modalities into a single shared vector space. It functions as a cross-modal retrieval framework designed to bind multiple sensory inputs into one cohesive mathematical embedding. The system uses a contrastive learning architecture to align disparate data types by maximizing the similarity between related samples. This allows the model to perform zero-shot multimodal classification and execute cross-modal data retrieval, such as locating visual content via natural language descr

Moondream is a small-scale vision language model designed to reason across images to generate captions and answer natural language questions. It functions as an edge-optimized system capable of performing visual question answering, image captioning, and object detection. The project distinguishes itself through a lightweight architecture designed for local inference on embedded devices, workstations, and air-gapped hardware. It supports the execution of models on local GPUs and Apple Silicon to ensure data privacy and low latency. The system's capabilities include identifying precise object

zero_nlp is a distributed framework for training and fine-tuning large language models and multimodal architectures. It provides a specialized toolkit for distributed model parallelism, allowing neural network layers and weights to be partitioned across multiple GPU devices to train models that exceed the memory capacity of a single processor. The project distinguishes itself through a combination of high-throughput data pipelines and parameter-efficient tuning. It utilizes multi-threading and memory mapping to preprocess and stream datasets exceeding 100GB and implements memory-saving adapta

Neuraltalk is an automated image captioning system that generates natural language descriptions for images. It utilizes a deep learning model that integrates a pretrained convolutional neural network for visual feature extraction with a recurrent neural network decoder to produce text sequences. The project provides a full workflow for training and evaluating captioning models, including weight optimization via backpropagation and gradient descent. It includes tools for measuring caption accuracy by comparing generated text against reference descriptions. The system covers data preprocessing

Swin-Transformer is a deep learning framework designed for training and deploying hierarchical vision transformer models. It serves as a research library and toolkit for computer vision tasks, providing the infrastructure to build models that replace standard convolution operations with sliding window self-attention mechanisms. By utilizing a multi-scale feature hierarchy, the framework enables the processing of visual data at varying resolutions and spatial scales. The project distinguishes itself through its implementation of shifted window partitioning, which facilitates global information

Donut is an OCR-free document transformer and end-to-end document parser. It functions as a neural network that converts unstructured document images directly into structured data or text without the use of an external optical character recognition engine. The project includes a synthetic document generator to create artificial images and ground-truth labels for training. It employs a transformer model to perform visual question answering and document image classification based on visual layout and text. The system covers several document understanding capabilities, including structured info

Multimodal is a machine learning library built on PyTorch for training large-scale models that combine text, image, audio, and video data streams. It functions as a deep learning framework dedicated to generative diffusion models, multi-task training, and vision-language tasks. The library supplies modular building blocks, discrete latent codebook quantization, shared-space embeddings, and stackable adapter layers to handle diverse conditional inputs during training and inference. The framework supports specific architectures for diffusion models, text-to-video generation, image-text retrieva

EasyR1 is a distributed model training system and reinforcement learning framework for large language and vision-language models. It functions as a multimodal trainer and an implementation of a Proximal Policy Optimization pipeline designed to refine the reasoning and perception capabilities of models that process both text and images. The system specializes in distributing reinforcement learning workloads across multiple compute nodes to manage high memory requirements. It optimizes hardware utilization through padding-free training and fine-tuning to fit large models onto available graphics

Open Flamingo is a multimodal large language model training framework designed to integrate pretrained vision encoders with language models. It implements a vision-language architecture that utilizes cross-attention layers to process interleaved sequences of images and text. The system is characterized by its few-shot multimodal learning capabilities, allowing the model to adapt to new visual tasks using a small set of image-text examples provided in the prompt. It supports in-context learning and multimodal text generation for tasks such as visual question answering and captioning. The fram

VLM-R1 is a reasoning vision-language model and embodied AI framework designed to map visual inputs and language instructions into physical navigation waypoints and robotic actions. It functions as a multimodal policy optimizer and an open vocabulary detector capable of locating objects based on arbitrary natural language descriptions. The system distinguishes itself through the use of chain-of-thought reasoning and reinforcement learning to solve complex visual and spatial tasks. It utilizes a video semantic memory system, which employs a visual cache to maintain a history of live video for

This project is a research framework and toolkit designed for training large-scale vision transformers and multimodal language models. It provides a comprehensive suite for vision-language pretraining, enabling the development of models that map images and text into shared latent spaces. The framework is distinguished by its capabilities in high-fidelity image generation and multimodal research, utilizing normalizing flows and variational autoencoders to produce images from text prompts or class labels. It supports the development of both generative and contrastive models, allowing for a wide

CogVLM is a multimodal large language model designed to integrate visual and textual data for reasoning about images and generating natural language. It functions as a visual question answering system that analyzes image content to provide detailed descriptions or answer specific questions. The project includes a visual grounding model capable of mapping text descriptions to precise bounding box coordinates within an image. It also features a vision-based automation agent that analyzes screen captures to generate execution plans and interaction coordinates for software interfaces. The system

DeepSeek-VL is a multimodal large language model and image-to-text reasoning engine. It functions as a vision-language model and visual question answering system that integrates visual perception with linguistic reasoning to understand and describe images. The project enables multimodal image understanding and document image analysis, specifically processing screenshots of web pages and technical diagrams. It provides capabilities for visual conversational AI, allowing users to interact with visual data to extract insights and perform complex reasoning across different types of visual informa

DeepSeek-VL2 is a multimodal large language model and vision-language system designed to analyze visual scenes and generate descriptive text. It functions as a visual question answering and visual grounding model, capable of extracting information from documents and locating specific objects or regions within images based on textual descriptions. The project utilizes a mixture-of-experts architecture to process combined image and text inputs. It is optimized for inference through incremental prefilling, which reduces the GPU memory requirements on hardware. The model covers multimodal data a

Recognize-anything is a multimodal foundation model designed for image recognition, visual tagging, and the generation of descriptive text captions from visual input. It functions as a multimodal embedding model that maps images and text into a shared vector space to enable cross-modal retrieval and recognition. The system implements zero-shot image classification and open-vocabulary object detection, allowing it to recognize object categories not present in the original training data through custom label embeddings. It also features a visual tagging engine and a captioning system that produc

ai-edu is a comprehensive AI education curriculum and machine learning courseware collection. It provides theoretical tutorials, deep learning lab exercises, and project blueprints designed to teach artificial intelligence fundamentals through a combination of study and practical implementation. The project focuses on a learning-by-doing approach, guiding users from Python programming and neural network basics to advanced topics. It includes specialized instructional content on distributed AI training, MLOps educational guides for model quantization and pruning, and detailed frameworks for im

SmolLM is a project dedicated to the development of small language models. It focuses on training and fine-tuning compact models that maintain high performance while utilizing fewer parameters. The project emphasizes efficient AI inference and on-device text generation, aiming to enable the deployment of lightweight models on edge devices with limited memory and processing power. It utilizes synthetic data generation to produce artificial datasets that improve the reasoning and training of these AI systems. The system supports a variety of optimization and training capabilities, including we

This project provides a foundational framework and reference implementation for executing causal language modeling and multimodal reasoning on local systems. It includes a set of core components for managing model assets, a fine-tuning framework, and structural definitions required to instantiate transformer-based architectures. The system is distinguished by its ability to process combined text and image inputs through multimodal transformer models for visual reasoning and document analysis. It also supports the deployment of quantized models, reducing memory footprints through low-precision

LAVIS is a multimodal large language model framework and vision-language model library. It provides tools for training and evaluating models that integrate visual, textual, and audio data, serving as a cross-modal feature extractor and a zero-shot visual reasoning engine. The framework distinguishes itself by using frozen-backbone integration, where pretrained encoders remain non-trainable while lightweight adapter layers are updated. It employs cross-modal feature alignment to map different representations into a shared embedding space and utilizes a modular model wrapper to swap vision and

Ignite is a high-level training framework for PyTorch neural networks that serves as a training engine and deep learning lifecycle manager. It provides a structured system for organizing and automating training and evaluation loops, managing data iterators and triggering event handlers at specific milestones during the model training process. The project distinguishes itself through a comprehensive suite of tools for distributed training and model evaluation. It includes utilities for synchronizing gradients and coordinating collective communication across multiple GPUs or nodes, as well as a

Composer is a PyTorch distributed training framework designed for scaling large-scale models across multi-node GPU clusters. It functions as a large language model trainer, a distributed model optimizer, and a training lifecycle manager. The project differentiates itself as a deep learning regularization library, providing specialized optimization techniques such as Sharpness Aware Minimization, MixUp, and CutMix to improve model generalization. It further distinguishes its training flow through the use of sequence length warmup, progressive layer freezing, and sharded-state checkpointing for

This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This