Search FoxAI

AI Models 84753

• stt_nl_fastconformer_hybrid_large_pc↗

  NVIDIA

• ner-rubert-tiny-news-ONNX↗

  onnx-community

• Qwen2.5-0.5B-Instruct-ONNX↗

  onnx-community

• AgentCPM-Report↗

  openbmb

• InternVL-Chat-ViT-6B-Vicuna-7B↗

  OpenGVLab

• tiny-random-mistral↗

  optimum-intel-internal-testing

• tiny_OPTForSequenceClassification-lora↗

  peft-internal-testing

• rtdetr_v2_r50vd↗

  PekingU

  The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augmentation and scale-adaptive hyperparameters. These changes enhance flexibility and practicality while maintaining real-time performance. This model was contributed by @jadechoghari with the help of @cyrilvallez and @qubvel-hf RT-DETRv2 consistently outperforms its predecessor across all model sizes while maintaining the same real-time speeds.

• KnowLine-4B-Gen5.5↗

  PelaAI

• DeepSeek-V4.1-Flash-GSQ-RCO-GGUF↗

  pfeifferj

  > **TL;DR:** DeepSeek's 552B-parameter backbone plus 196B-parameter Engram memory, reduced from the original 510.3 GB FP8/FP4 checkpoint to a 426.1 GB package including the DSpark draft model and vision projector. **Non-uniform GGUF quantization** produced with **GSQ** and **RCO**, with the DSpark draft model and the vision projector. > Independent community reproduction. These files were produced by a third party using the published GSQ and RCO methods. They are not an IST-DASLab release and carry no endorsement from the authors of either paper.