全站搜索

AI 模型 85003

• Nanonets-OCR2-3B-GGUF↗

  Mungert

• HyperCLOVAX-SEED-Vision-Instruct-3B-GGUF↗

  naver-ellm

• Llama-3.2-1B-pruned-40pct↗

  oopere

• OpenMed-NER-SpeciesDetect-TinyMed-82M↗

  OpenMed

  **Specialized model for Species Entity Recognition - Species and organism names** This model is a **state-of-the-art** fine-tuned transformer engineered to deliver **enterprise-grade accuracy** for species entity recognition - species and organism names. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as **drug interaction detection**, **medication extraction from patient records**, **adverse event monitoring**, **literature mining for drug discovery**, and **biomedical knowledge graph construction** with **production-ready reliability** for clinical and research applications. - **High Precision**: Optimized for biomedical entity recognition - **Domain-Specific**: Trained on curated LINNAEUS dataset - **Production-Ready**: Validated on clinical benchmarks - **Easy Integration**: Compatible with Hugging Face Transformers ecosystem

• AETHER-Mythos-1-1.2B↗

  orangejuicesmith

• eeg-fm-masking_jepa_r9cm_L2↗

  PierreGtch

• paraphrase-multilingual-MiniLM-L12-v2-onnx-Q↗

  Qdrant

  Quantized ONNX port of sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 for text classification and similarity searches. Here's an example of performing inference using the model with FastEmbed.

• ESRGAN↗

  qualcomm

• MediaPipe-Face-Detection↗

  qualcomm

• Jev-Omni-Q4_K_M-GGUF↗

  Reza2kn

  The quantized backbone is **6.87 GiB on disk** (7,381,382,848 bytes). The multimodal projector adds 116.38 MiB, and the required FP32 decision head adds 3.78 MiB. GPU figures are `nvidia-smi` readings for the llama.cpp process on an RTX 5080 Laptop GPU with full offload and 2,048 context. CPU text used 1,024 context; CPU video used 8,192 context. These are observed readings, not maximums across all inputs and settings. Allow additional memory for the OS and other programs. This is a Q4_K_M quantization of `akhilaaa3/Jev-Omni`, source revision `c050d51354147985d13286cf4acf90f562f2c631`. Its Gemma 4 12B backbone was converted with llama.cpp revision `6e60f35608ec6918b44a9839c0c433687165f086` and quantized with `llama-quantize ... Q4_K_M 8`, without an importance matrix. The quantizer reported **4.95 bits per weight overall**; Q4_K_M is a mixed-precision format, not exactly four bits for every tensor. The multimodal projector and decision head retain their original precision.