从语言到影像，从开源到 API。读懂模型能力、比较真实成本，
为你的下一个想法，找到合适的智能引擎。
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
A Vision Transformer (ViT) image classification model. \ Trained on 33M histology patches from various pathology datasets.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
Smaug-AI-Image-Detector sets a new state of the art for open-source AI-generated image detection. It is a fine-tune of Google's EmbeddingGemma-2 by Abacus.AI and the strongest open-source detector on real-world images. **A dedicated vision model, 41% smaller than its base.** We streamlined EmbeddingGemma-2 into a vision-only architecture by removing its 305M-parameter audio tower: 439M parameters instead of 744M, with no loss in accuracy. Architecture EmbeddingGemma-2 image encoder + linear classifier Total Parameters 439M (base model: 744M) Audio Tower Removed: vision-only architecture, −305M parameters Input Any image; scored as three 528 × 528 crops at native resolution Output Probability that the image is AI-generated Hardware NVIDIA GPU (~1 GB), Apple Silicon (Metal), or CPU Precision bfloat16 weights Formats PyTorch / sentence-transformers (this repo); GGUF for llama.cpp: Smaug-AI-Image-Detector-GGUF Base Model google/embeddinggemma-2 Adaptation Full fine-tune
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
A state-of-the-art Vision Transformer model for simultaneous age estimation and gender classification, achieving **94.3% gender accuracy** and **4.5 years age MAE** on the UTKFace dataset. ✅ **Issue Resolved:** Model now includes helper functions that return proper age and gender values (not `LABEL_0`/`LABEL_1`) **Important:** These helper functions work correctly. The standard `pipeline()` approach returns `LABEL_0`/`LABEL_1` and should not be used.
译文排队中 · 当前显示来源原文
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the AI-Lab-Makerere/beans dataset. It achieves the following results on the evaluation set: - Loss: 0.0988 - Accuracy: 0.9699 - F1 Macro: 0.9699 The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 5 - mixed_precision_training: Native AMP
译文排队中 · 当前显示来源原文
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the AI-Lab-Makerere/beans dataset. It achieves the following results on the evaluation set: - Loss: 0.0619 - Accuracy: 0.9850 - F1 Macro: 0.9850 The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 64 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 5 - mixed_precision_training: Native AMP
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
Recognises one handwritten Gurmukhi digit (੦ ੧ ੨ ੩ ੪ ੫ ੬ ੭ ੮ ੯) in an image. It is the model behind the digit recognition on AI Panjab. **Try it without code:** the Space: draw a digit and get the top three guesses. The Space also has a **Use via API** page (Python, JavaScript, curl). 1. a transparent background (RGBA) is put on white; any other image is converted to RGB; 2. grayscale with the ITU-R 601 weights: `0.2989 R + 0.5870 G + 0.1140 B`, kept in floating point; 3. resized to 28 x 28 with bilinear (antialiased) resizing.
译文排队中 · 当前显示来源原文
Model CNN hasil *fine-tuning* ResNet-50 (pra-terlatih ImageNet) untuk mengklasifikasikan gambar pemandangan ke dalam 6 kelas: buildings, forest, glacier, mountain, sea, street. Intel Image Classification (Kaggle) — sekitar 14 ribu gambar latih (dibagi 85% train / 15% validasi) dan 3 ribu gambar uji, ukuran 150×150.
译文排队中 · 当前显示来源原文
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
可以调整厂商、分类或输入输出条件；新模型正持续收录。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。
