This is an uncensored version of Qwen/Qwen3-VL-8B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). The abliterated model will no longer say "I can’t describe or analyze this image." **Please update to the latest version of Ollama-v0.12.7.** You can use huihui_ai/qwen3-vl-abliterated:8b-instruct directly,
--- license_name: qwen-research license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE language: - en pipeline_tag: image-text-to-text tags: - multimodal - abliterated - uncensored library_name: transformers base_model: - Qwen/Qwen2.5-VL-3B-Instruct --- This is an uncensored version of Qwen/Qwen2.5-VL-3B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). You can use huihui_ai/qwen2.5-vl-abliterated:3b directly,
--- license: apache-2.0 language: - en pipeline_tag: image-text-to-text tags: - multimodal - abliterated - uncensored library_name: transformers base_model: - Qwen/Qwen2.5-VL-7B-Instruct --- This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). You can use huihui_ai/qwen2.5-vl-abliterated:7b directly,
**lightvl Developed by Myself is a lightweight Vision-Language Model (VLM) quantization toolkit supporting FP8, INT8, FP8-Block. It integrates with vLLM for high-throughput inference and supports Qwen3-VL, Qwen3.5, InternVL-Chat, and Gemma-4 models.** > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.
**Model Summary:** Granite-4.0-3B-Vision is a vision-language model (VLM) designed for enterprise-grade document data extraction. It focuses on specialized, complex extraction tasks that ultracompact models often struggle with: - **Chart extraction:** Converting charts into structured, machine-readable formats (Chart2CSV, Chart2Summary, and Chart2Code) - **Table extraction:** Accurately extracting tables with complex layouts from document images to JSON, HTML, or OTSL - **Semantic Key-Value Pair (KVP) extraction:** Extracting values based on key names and descriptions across diverse document layouts The model is delivered as a LoRA adapter on top of Granite 4.0 Micro, with a 3.5B base LLM and 0.5B LoRA adapters. This enables a single deployment to support both multimodal document understanding and text-only workloads — the base model handles text-only requests without loading the adapter. See Model Architecture for details.
Granite Docling is a multimodal Image-Text-to-Text model engineered for efficient document conversion. It preserves the core features of Docling while maintaining seamless integration with DoclingDocuments to ensure full compatibility. Granite Docling 258M builds upon the Idefics3 architecture, but introduces two key modifications: it replaces the vision encoder with siglip2-base-patch16-512 and substitutes the language model with a Granite 165M LLM. Try out our Granite-Docling-258 demo today. - **Developed by**: IBM Research - **Model type**: Multi-modal model (image+text-to-text) - **Language(s)**: English (NLP) - **License**: Apache 2.0 - **Release Date**: September 17, 2025
**Model Summary:** granite-vision-3.2-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more. The model was trained on a meticulously curated instruction-following dataset, comprising diverse public datasets and synthetic datasets tailored to support a wide range of document understanding and general image tasks. It was trained by fine-tuning a Granite large language model with both image and text modalities. We evaluated Granite Vision 3.2 alongside other vision-language models (VLMs) in the 1B-4B parameter range using the standard llms-eval benchmark. The evaluation spanned multiple public benchmarks, with particular emphasis on document understanding tasks while also including general visual question-answering benchmarks. **Supported Input Format:** Currently the model supports English instructions and images (png, jpeg, etc.) as input format.
**Model Summary:** Granite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint, providing a lightweight alternative to much larger frontier models for these tasks: - **Chart extraction:** Converting charts into structured, machine-readable formats (Chart2CSV, Chart2Summary, and Chart2Code) - **Table extraction:** Accurately extracting tables with complex layouts from document images to JSON, HTML, or OTSL - **Semantic Key-Value Pair (KVP) extraction:** Extracting values based on key names and descriptions across diverse document layouts The model is finetuned on top of Granite-4.1-3B, with a 3.4B LLM and 0.6B Vision Encoder and Projectors. See Model Architecture for details.
DeepSeek-V4.1-Flash-1017 (552B MoE + 196B Engram) quantized to **187.6 GB**, intended for two RTX 3090s and 192 GB of RAM with exact routing. Runs on **dsx**, a Rust + CUDA engine made for this model. This is a V4.1 GSQ GGUF for dsx, not a llama.cpp / Ollama / LM Studio GGUF. Measured with `dsx eval` on Lucebox's 1017 eval set: 8 × 1024 held-out tokens, KL and top-1 against the FP8/FP4 teacher's top-256 log-probs. All experts were resident (`0 left in the file`). Measured on this machine with the new `dsx` engine: 2× RTX 3090, 192 GB RAM, NVMe SSD, `--ctx 262144`, all experts resident.