Search FoxAI
AI Models 84760
- InternVL3_5-30B-A3B↗
OpenGVLab
We introduce *InternVL3.5*, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the *Cascade Reinforcement Learning (Cascade RL)* framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g., MMMU and MathVista. To optimize efficiency, we propose a *Visual Resolution Router (ViR)* that dynamically adjusts the resolution of visual tokens without compromising performance. Coupled with ViR, our Decoupled *Vision-Language Deployment (DvD)* strategy separates the vision encoder and language model across different GPUs, effectively balancing computational load. These contributions collectively enable InternVL3.5 to achieve up to a +16.0\% gain in overall reasoning performance and a 4.05 \\(\times\\) inference speedup compared to its predecessor, i.e., InternVL3. In addition, InternVL3.5 supports novel capabilities such as GUI interaction and embodied agency. Notably, our largest model, i.e., InternVL3.5-241B-A28B, attains state-of-the-art results among open-source MLLMs across general multimodal, reasoning, text, and agentic tasks—narrowing the performance gap with leading commercial models like GPT-5. All models and code are publicly released. > Hatched bars represent closed-source commercial models. We report average scores on a set of multimodal general, reasoning, text, and agentic benchmarks: MMBench v1.1 (en), MMStar,BLINK, HallusionBench, AI2D, OCRBench, MMVet, MME-RealWorld (en), MVBench, VideoMME, MMMU, MathVista, MathVision, MathVerse, DynaMath, WeMath, LogicVista, MATH500, AIME24, AIME25, GPQA, MMLU-Pro, GAOKAO, IFEval, SGP-Bench, VSI-Bench, ERQA, SpaCE-10, and OmniSpatial. In the following table, we provide an overview of the InternVL3.5 series. To maintain consistency with earlier generations, we provide two model formats: the GitHub format, consistent with prior releases, and the HF format, aligned with the official Transformers standard.
- OpenMed-NER-DNADetect-ModernClinical-395M↗
OpenMed
**Specialized model for Biomedical Entity Recognition - Proteins, DNA, RNA, cell lines, and cell types** This model is a **state-of-the-art** fine-tuned transformer engineered to deliver **enterprise-grade accuracy** for biomedical entity recognition - proteins, dna, rna, cell lines, and cell types. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as **drug interaction detection**, **medication extraction from patient records**, **adverse event monitoring**, **literature mining for drug discovery**, and **biomedical knowledge graph construction** with **production-ready reliability** for clinical and research applications. JNLPBA corpus focuses on biomedical named entity recognition for protein, DNA, RNA, cell line, and cell type entities.
- OpenMed-ZeroShot-NER-Genomic-Tiny-60M↗
OpenMed
Targets **gene and genetics entities**, handling symbol/name variants commonly found in genomics literature.Useful for **genetic association studies**, **variant curation**, and **genomics informatics**. OpenMed ZeroShot NER is an advanced, domain-adapted Named Entity Recognition (NER) model designed specifically for medical, biomedical, and clinical text mining. Leveraging state-of-the-art zero-shot learning, this model empowers researchers, clinicians, and data scientists to extract expert-level biomedical entities—such as diseases, chemicals, genes, species, and clinical findings—directly from unstructured text, without the need for task-specific retraining. Built on the robust GLiNER architecture and fine-tuned on curated biomedical corpora, OpenMed ZeroShot NER delivers high-precision entity recognition for critical healthcare and life sciences applications. Its zero-shot capability means you can flexibly define and extract any entity type relevant to your workflow, from standard biomedical categories to custom clinical concepts, supporting rapid adaptation to new research domains and regulatory requirements.
- MOSS-TTS-Local-Transformer↗
OpenMOSS-Team
MOSS‑TTS Family is an open‑source **speech and sound generation model family** from MOSI.AI and the OpenMOSS team. It is designed for **high‑fidelity**, **high‑expressiveness**, and **complex real‑world scenarios**, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS. When a single piece of audio needs to **sound like a real person**, **pronounce every word accurately**, **switch speaking styles across content**, **remain stable over tens of minutes**, and **support dialogue, role‑play, and real‑time interaction**, a single TTS model is often not enough. The **MOSS‑TTS Family** breaks the workflow into five production‑ready models that can be used independently or composed into a complete pipeline. - **MOSS‑TTS**: The flagship production model featuring high fidelity and optimal zero-shot voice cloning. It supports **long-speech generation**, **fine-grained control over Pinyin, phonemes, and duration**, as well as **multilingual/code-switched synthesis**. - **MOSS‑TTSD**: A spoken dialogue generation model for expressive, multi-speaker, and ultra-long dialogues. The new **v1.0 version** achieves **industry-leading performance on objective metrics** and **outperformed top closed-source models like Doubao and Gemini 2.5-pro** in subjective evaluations. You can visit the MOSS-TTSD repository for details. - **MOSS‑VoiceGenerator**: An open-source voice design model capable of generating diverse voices and styles directly from text prompts, **without any reference speech**. It unifies voice design, style control, and synthesis, functioning independently or as a design layer for downstream TTS. Its performance **surpasses other top-tier voice design models in arena ratings**. - **MOSS‑TTS‑Realtime**: A multi-turn context-aware model for real-time voice agents. It uses incremental synthesis to ensure natural and coherent replies, making it **ideal for building low-latency voice agents when paired with text models**. The TTFB (Time To First Byte) of MOSS-TTS-Realtime reaches 180 ms, and the $T_{\text{LLM-first-sentence}} + T_{\text{MOSS-TTS-Realtime-TTFB}}$ is 377 ms. - **MOSS‑SoundEffect**: A content creation model specialized in **sound effect generation** with wide category coverage and controllable duration. It generates audio for natural environments, urban scenes, biological
- BERTAIDetector↗
pritamdeb68
This model is a fine-tuned BERT designed to classify text as either AI-generated or human-written. The model was trained on data from the Kaggle LLM Detect competition using variable-length text inputs ranging from 5 to 100 words. The fine-tuned model achieves high accuracy in identifying the source of the text, making it a valuable tool for detecting AI-generated content. - **Developed by:** Pritam - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Finetuned from model:** BERT (base-uncased) - **Repository:** Hugging Face Model Card - **Demo:** Streamlit Interface
- HelpingAI-15B-GGUF↗
QuantFactory
- Llama-3.1-8B-EZO-1.1-it-GGUF↗
QuantFactory
- Krea2-Serendipity-V2↗
Raxephion
- Inkling-NVFP4-FP8-BLOCK↗
RedHatAI
- adamo1139_-_Yi-6B-200K-AEZAKMI-v2-gguf↗
RichardErkhov
