LLM Models · inclusionAI
Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.
SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
🤗 Hugging Face 🤖 ModelScope Tech Report 🐙 GitHub
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
Ling is a MoE LLM provided and open-sourced by InclusionAI. We introduce two different sizes, which are Ling-Lite and Ling-Plus. Ling-Lite has 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus has 290 billion parameters with 28.8 billion activated pa…
UI-Venus-1.5 model This repository contains the UI-Venus model from the report UI-Venus-1.5 Technical Report. UI-Venus 1.5 is a unified, end-to-end GUI Agent designed for robust real-world applications. The model family includes two dense (2B/8B) and one MoE (30B-A3B) variants to…
ArmorOCR is a two-stage framework for grounded adversarial OCR perception built on Qwen3-VL-8B-Instruct. It enables single-pass inference on the original image, without any inference-time visual transformations or tool assistance.
Ling is a MoE LLM provided and open-sourced by InclusionAI. We introduce two different sizes, which are Ling-Lite and Ling-Plus. Ling-Lite has 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus has 290 billion parameters with 28.8 billion activated pa…
🤗 Hugging Face 🤖 ModelScope Tech Report 💻 GitHub
LLaDA2.0-mini-CAP is an enhanced version of LLaDA2.0-mini that incorporates Confidence-Aware Parallel (CAP) Training for significantly improved inference efficiency. Built upon the 16B-A1B Mixture-of-Experts (MoE) diffusion architecture, this model achieves faster parallel decodi…
UI-Venus This repository contains the UI-Venus model from the report UI-Venus Technical Report: Building High-performance UI Agents with RFT.
ZwZ-4B is a fine-grained multimodal perception model built upon Qwen3-VL-4B. It is trained using Region-to-Image Distillation (R2I) combined with reinforcement learning, enabling superior fine-grained visual understanding in a single forward pass — no inference-time zooming or to…
ZwZ-8B is a fine-grained multimodal perception model built upon Qwen3-VL-8B. It is trained using Region-to-Image Distillation (R2I) combined with reinforcement learning, enabling superior fine-grained visual understanding in a single forward pass — no inference-time zooming or to…