전체 검색

AI 모델 84757

• qwen3.6-35b-a3b-crown-halo-mtp-dynamic↗

  jcbtc

• phi-4-DASHQ-Q2-GGUF↗

  jkim96

• llama3.1-8b-16x4-emo-style-routed-lora-moe↗

  Jongbin-kr

• Nemotron-3-Nano-Omni-AEON-Ultimate-Uncensored-BF16-Q3_K_M-GGUF↗

  kainecorneko

• fairseq-dense-2.7B↗

  KoboldAI

• yolov8-license-plate-detection↗

  Koushim

  This repository contains a YOLOv8 object detection model trained to detect **license plates** in real-world images. The model was trained using the Ultralytics YOLOv8 framework and can be deployed for real-time applications such as surveillance, traffic monitoring, and vehicle identification. - **Architecture**: YOLOv8n (Nano variant) - **Framework**: Ultralytics YOLOv8 - **Task**: Object Detection - **Classes**: 1 (`license_plate`) - **Input resolution**: 640×640 - **File**: `best.pt`

• NeuralExperiment-7b-MagicCoder-v7.5↗

  Kukedlc

  This model is an experimental AI trained on three distinct datasets focusing on logical reasoning, mathematics, and programming. The training process involved fine-tuning from the last layer (31) backward with a gradually decreasing learning rate. The primary goal is to address and rectify the common 'INSTINST' bug observed in leaderboard models through targeted training on the latest layers. Each dataset contributed 20,000 data points to the training process, ensuring a balanced representation of logic, mathematics, and programming tasks.

• ko-sroberta-multitask-stockmatching↗

  kwoncho

• qwen-metaphor-unke-camada-8-literal-metaforica↗

  luisastellet

• Gemmasutra-Mini-2B-v1_iMatrix_GGUF↗

  MarsupialAI