全站搜索

AI 模型 84759

• FuseCap_Image_Captioning↗

  noamrot

• corrdiff-cosmo-era5↗

  NVIDIA

• Ising-Calibration-1.5-31B-NVFP4↗

  NVIDIA

• Kimodo-G1-RP-v1↗

  NVIDIA

• stt_ru_fastconformer_hybrid_large_pc↗

  NVIDIA

• Omni-Edu-9B↗

  OmniEdu

• VideoChat-Flash-Qwen2-7B_res448↗

  OpenGVLab

  VideoChat-Flash-7B is constructed upon UMT-L (300M) and Qwen2-7B, employing only **16 tokens per frame**. By leveraging Yarn to extend the context window to 128k (Qwen2's native context window is 32k), our model supports input sequences of up to approximately **10,000 frames**. > Note: Due to a predominantly English training corpus, the model only exhibits basic Chinese comprehension, to ensure optimal performance, using English for interaction is recommended. First, you need to install flash attention2 and some other modules. We provide a simple installation example below:

• OpenScholar_Retriever↗

  OpenSciLM

• EuroDense-435M↗

  OPI-PIB

• tiny-random-llama↗

  optimum-internal-testing