Tag
Explore by tags
Instruction-tuned Mixture-of-Experts multimodal model that generates text from text+image inputs while activating a 4B subset of parameters for faster inference; supports a 256K context window, multilingual vision-language tasks, and is available under Apache-2.0.
Transforms articulated 3D asset creation into a programmatic, LLM-driven code-generation workflow that produces objects with semantic parts, robust geometry, and physical joints. Includes CLI generation, a local viewer, and pipelines for large-scale dataset contribution.
Pretrained image-model checkpoint hosted on Hugging Face by Facebook (Meta) for vision experiments and transfer learning. Includes downloadable weights and metadata under CC BY‑NC 4.0 — suitable for research and prototyping but restricted for commercial use.
Large-scale mid-training corpora for multimodal models: 10,809 ~60s video shards, caption splits (30s/60s/180s/>10min), 84 spatial-reasoning shards, and CSV mappings to source YouTube IDs. Small Parquet preview configs are provided for schema inspection.
Runs the Bonsai family of quantized LLMs locally (including vision-capable 27B): provides scripts and demo UIs to run 1-bit and ternary Bonsai models on macOS (Metal), Linux/Windows (CUDA/Vulkan/ROCm), or CPU, with long context, tool-calling and an optional Open WebUI agent demo.
Provides a diagnostic suite that audits video-understanding benchmarks to find samples solvable without visual or temporal input, filters those shortcuts, and produces a distilled video-native testbed that reveals major capability gaps in current Video-LLMs.
Provides curated short video clips (49- and 81-frame) with layered ground truth—edit layers, alpha mattes, and composite targets—for training and evaluating content-preserving layered diffusion video editing. Contains background-replace and object-add edits; Apache-2.0 licensed.
Multimodal image-text-to-text fork of Gemma 4 (31B) using a 'CRACK v2' abliteration — tuned for conversational vision inputs and thinking-mode support in JANG v2 safetensors format. Recommended to run in vMLX; published by dealignai.
Generates persistent, explorable 3D worlds from a single image by synthesizing long-range, geometry-consistent video and reconstructing it into an explicit 3D Gaussian scene. Intended for internal research use under NVIDIA's research license.
An open text-to-image generation model built on an 8B Diffusion Transformer that focuses on layout-sensitive, text-heavy, and instruction-following image synthesis. Notable for accurate text rendering, structured/compositional generation (posters, comics), and ability to run on consumer 24GB GPUs when paired with prompt enhancement.
Provides 12.26M synthetically generated multilingual OCR samples (en/ja/ko/ru/zh) with word/line/paragraph bounding boxes and reading-order graphs, packaged as HDF5 shards for training detection, recognition, and layout models; licensed CC BY 4.0.
Benchmarks document-parsing systems on real-world enterprise PDFs and images—evaluates tables, charts, content faithfulness, semantic formatting, and visual grounding with human-verified, rule-level tests. Ships with ~2,000 pages, ~169K test rules, and an open evaluation framework for end-to-end pipeline scoring.