Search FoxAI
AI Models 85003
- Nemotron-3.5-Parse↗
NVIDIA
Nemotron 3.5 Parse is a document image parser that produces structured, machine-readable text with semantic layout classes, bounding boxes, and reading order. It combines a C-RADIOv4-SO400M vision encoder with a 10-layer mBART decoder that consumes the visual sequence as a causal prefix. The release uses dynamic rectangular NaViT preprocessing, content-normalized coordinates, grouped-query self-attention (16 query heads and 8 key/value heads), a 72,505-token multilingual tokenizer, and chart-aware output through the ` ` token. It is intended for document understanding, information retrieval, data extraction, and multimodal data-curation workflows. ParseBench results use triple pass with region union on 2,078 unique pages. See pipeline details, reproduction instructions, and evaluation results. MOSCAR uses simple synthetic renderings of text in each language to test basic OCR capability. These results do not guarantee accuracy on complex scanned documents, handwriting, degraded images, or other real-world variations. Character bag F1 measures character overlap without considering character order.
- Nemotron-3-Diarization↗
NVIDIA
**Nemotron 3 Diarization** is an open-weight speaker diarization model designed to determine "who spoke when" in real-world audio. It supports both streaming and offline inference and handles up to eight speakers. Following Sortformer [\[1\]](#ref-1), the model resolves speaker permutation by ordering its output channels according to each speaker's first arrival in the input audio. For streaming inference, the model adopts the Arrival-Order Speaker Cache (AOSC) and FIFO queue introduced in **Streaming Sortformer** [\[2\]](#ref-2). The AOSC retains speaker information from earlier chunks to preserve speaker identities over time, while the FIFO queue provides recent frame context for each processing step. A single checkpoint supports input buffer latency as low as 80 ms for latency-critical applications, although the lowest recommended configuration is 0.32 s; the offline-style configuration uses a 30.4 s input buffer. The output frame resolution is configurable in multiples of 10 ms. With chunked inference, the maximum audio duration is not limited.
- Forced_BJ↗
onamissiononamission
- gemma-3n-E2B-it-ONNX↗
onnx-community
- kev-4b-ONNX↗
onnx-community
- InternVL2_5-38B-MPO-AWQ↗
OpenGVLab
- InternVL2_5-8B↗
OpenGVLab
We are excited to introduce **InternVL 2.5**, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. As shown in the following figure, InternVL 2.5 retains the same model architecture as its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 2.5 and Qwen 2.5, using a randomly initialized MLP projector. As in the previous version, we applied a pixel unshuffle operation, reducing the number of visual tokens to one-quarter of the original. Besides, we adopted a similar dynamic resolution strategy as InternVL 1.5, dividing images into tiles of 448×448 pixels. The key difference, starting from InternVL 2.0, is that we additionally introduced support for multi-image and video data.
- InternVL2-Llama3-76B↗
OpenGVLab
- Ornith-1.5-122B-FP8↗
ornith-ai
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For more details on the task, harness, and rollout reward design, please refer to our blog. This model card documents **Ornith-1.5-122B**, the most capable and efficient.member of the Ornith-1.5 family — a 122B MOE model designed for efficient single-GPU deployment, and edge-deployable on mobile devices via its quantized Ornith-1.5-122B-Mobile variant.
- Nanbeige4.2-3B-GGUF↗
owao
See the original model card for details on how to use with llama.cpp and ollama (you'll need to build from their fork cause their changes didn't land in llama.cpp main yet). > Some of llama.cpp maintainers even have to work during their vacations just to have someone else copy their work without giving any credits. > it would have been much better if all projects that depend on @ggerganov's and the ggml team work would have upstreamed the contributions directly so anyone in the ecosystem could benefit, and avoid vendor lock-in and the duplicated efforts everywhere... consuming llama.cpp and reporting issues and upstream any change directly there. It is quite frustrating to see that the Open source scene is really getting derailed lately by this kind of bad attitude.