全站搜索
AI 模型 85003
- InternVideo2-Stage2-6B-Audio↗
OpenGVLab
- VideoChat-Flash-Qwen2-7B_res224↗
OpenGVLab
- stable-diffusion-3.5-large-DF11↗
Peter-jz
- Qwen3-1.7B↗
PrimeIntellect
This is a clone of `Qwen/Qwen3-1.7B` with a multi-turn, tool-call compatible chat template.
- inclusionAI-UI-Venus-2-9B-GGUF↗
prithivMLmods
- Q3.5-9B-OpusGLM-MAX-0731-ablated-GGUF↗
prithivMLmods
- Instinct-Python-Coder-Gemma4-12B-Qwen3.8-27B↗
projectj
- Qwen2.5-Math-72B↗
阿里巴巴 · Qwen
- Qwen2.5-Omni-3B↗
阿里巴巴 · Qwen
Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. * **Omni and Novel Architecture**: We propose Thinker-Talker architecture, an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner. We propose a novel position embedding, named TMRoPE (Time-aligned Multimodal RoPE), to synchronize the timestamps of video inputs with audio. * **Real-Time Voice and Video Chat**: Architecture designed for fully real-time interactions, supporting chunked input and immediate output.
- Qwen3.5-0.8B-Base↗
阿里巴巴 · Qwen
> [!Note] > This repository contains model weights and configuration files for the pre-trained only model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, etc. > > The intended use cases are fine-tuning, in-context learning experiments, and other research or development purposes, not direct interaction. > However, the control tokens, e.g., ` ` and ` ` were trained to allow efficient LoRA-style PEFT with the official chat template, mitigating the need to finetune embeddings, a significant optimization given Qwen3.5's larger vocabulary. 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. - **Unified Vision-Language Foundation**: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.