The NVIDIA DeepSeek-V4-Pro-NVFP4 model is the quantized version of the DeepSeek-V4-Pro model, which is a Mixture-of-Experts (MoE) language model with 1.6 trillion total parameters and 49 billion activated parameters. For more information, please check here. The NVIDIA DeepSeek V4 Pro NVFP4 model is quantized with Model Optimizer. This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA (DeepSeek V4 Pro) Model Card. DeepSeek V4 is well-suited for advanced reasoning, agentic AI applications, tool use scenarios, and complex problem-solving in domains such as mathematics, software engineering, and enterprise AI assistants.
A new version of Sortformer diarization model Nemotron-3-Diarization has been released, supporting 8 speakers and greatly improved accuracy. Sortformer resolves permutation problem in diarization following the arrival-time order of the speech segments from each speaker. For documentation, deployment guides, enterprise-ready APIs, and the latest open models—including Nemotron and other cutting-edge speech, translation, and generative AI—visit the NVIDIA Developer Portal at developer.nvidia.com. Join the community to access tools, support, and resources to accelerate your development with NVIDIA’s NeMo, Riva, NIM, and foundation models.
A new version of Sortformer diarization model Nemotron-3-Diarization has been released, supporting 8 speakers and greatly improved accuracy. This model is a streaming version of Sortformer diarizer. Sortformer[1] is a novel end-to-end neural model for speaker diarization, trained with unconventional objectives compared to existing end-to-end diarization models. Sortformer resolves permutation problem in diarization following the arrival-time order of the speech segments from each speaker.
A new version of Sortformer diarization model Nemotron-3-Diarization has been released, supporting 8 speakers and greatly improved accuracy. This model is a streaming version of Sortformer diarizer. Sortformer[1] is a novel end-to-end neural model for speaker diarization, trained with unconventional objectives compared to existing end-to-end diarization models. Streaming Sortformer[2] employs an Arrival-Order Speaker Cache (AOSC) to store frame-level acoustic embeddings of previously observed speakers.
--- pipeline_tag: text-generation base_model: google/diffusiongemma-26B-A4B-it license: apache-2.0 license_name: apache-license-2.0 license_link: https://ai.google.dev/gemma/apache_2 tags: - nvidia - ModelOpt - DiffusionGemma-26B-A4B-IT - quantized - NVFP4 - nvfp4 --- DiffusionGemma 26B A4B IT is an open-weights multimodal generative model developed by Google DeepMind that processes text, image, and video inputs to produce text output via discrete diffusion. Built on the Gemma 4 26B A4B Mixture-of-Experts (MoE) architecture with 25.2B total parameters and 3.8B active parameters, the model employs an encoder-decoder design with bidirectional attention that generates tokens in parallel 256-token blocks, enabling high-speed generation exceeding 1,100 tokens per second at low batch sizes on NVIDIA Hopper H100 (FP8). DiffusionGemma 26B A4B IT supports a 256K token context window, configurable thinking (reasoning) mode, native function calling, and multilingual inference across 35+ languages. The NVIDIA DiffusionGemma 26B A4B IT NVFP4 model is quantized with Model Optimizer. This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA DiffusionGemma 26B A4B Model Card.
CVPR 2025 (Oral) **Code** | **Project Page** | **Paper** Please visit the Difix3D repository to access all relevant files and code needed to use Difix Difix is a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views caused by underconstrained regions of 3D representation. The technology behind Difix is based on the concepts outlined in the paper titled DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models.
Difix is a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views caused by underconstrained regions of 3D representation. The technology behind Difix is based on the concepts outlined in the paper titled DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models. Difix is an all-encompassing solution, a single model compatible for both NeRF and 3DGS representations. The use of the model and code is governed by the NVIDIA License. Additional Information: LICENSE.md · stabilityai/sd-turbo at main
Model was trained in multiple rounds using Wikipedia and Common Crawl data, labeled by a combination of pseudo labels and Google Cloud API. The model outputs one of the 26 domain classes as the predicted domain for each input sample. Example output: The inference code is available on NeMo Curator's GitHub repository. Check out this example notebook to get started.
We introduce Dragon-multiturn, a retriever specifically designed for the conversational QA scenario. It can handle conversational query which combine dialogue history with the current query. It is built on top of the Dragon retriever. The details of Dragon-multiturn can be found in here. **Please note that Dragon-multiturn is a dual encoder consisting of a query encoder and a context encoder. This repository is only for the context encoder of Dragon-multiturn for getting the context embeddings, and you also need the query encoder to get query embeddings, which can be found here. Both query encoder and context encoder share the same tokenizer.** .tg {border:none;border-collapse:collapse;border-spacing:0;} .tg td{border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px;overflow:hidden; padding:10px 5px;word-break:normal;} .tg th{border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px;font-weight:normal; overflow:hidden;padding:10px 5px;word-break:normal;} .tg .tg-c3ow{border-color:inherit;text-align:center;vertical-align:center} .tg .tg-0pky{border-color:inherit;text-align:left;vertical-align:center} top-1 top-5 top-1 top-5 top-1 top-5 top-1 top-5 top-5* top-20* top-5* top-20*
We introduce Dragon-multiturn, a retriever specifically designed for the conversational QA scenario. It can handle conversational query which combine dialogue history with the current query. It is built on top of the Dragon retriever. The details of Dragon-multiturn can be found in here. **Please note that Dragon-multiturn is a dual encoder consisting of a query encoder and a context encoder. This repository is only for the query encoder of Dragon-multiturn for getting the query embeddings, and you also need the context encoder to get context embeddings, which can be found here. Both query encoder and context encoder share the same tokenizer.** .tg {border:none;border-collapse:collapse;border-spacing:0;} .tg td{border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px;overflow:hidden; padding:10px 5px;word-break:normal;} .tg th{border-style:solid;border-width:1px;font-family:Arial, sans-serif;font-size:14px;font-weight:normal; overflow:hidden;padding:10px 5px;word-break:normal;} .tg .tg-c3ow{border-color:inherit;text-align:center;vertical-align:center} .tg .tg-0pky{border-color:inherit;text-align:left;vertical-align:center} top-1 top-5 top-1 top-5 top-1 top-5 top-1 top-5 top-5* top-20* top-5* top-20*
