Add LiteRT converted eva02_large_patch14_448.mim_in22k_ft_in22k_in1k

README.md

@@ -0,0 +1,71 @@
+---
+library_name: litert
+base_model: timm/eva02_large_patch14_448.mim_in22k_ft_in22k_in1k
+license: mit
+tags:
+  - vision
+  - image-classification
+  - timm
+datasets:
+  - imagenet-1k
+---
+
+# eva02_large_patch14_448.mim_in22k_ft_in22k_in1k
+
+Converted TIMM image classification model for LiteRT.
+
+- Source architecture: `eva02_large_patch14_448`
+- Source checkpoint: `timm/eva02_large_patch14_448.mim_in22k_ft_in22k_in1k`
+- File: `model.tflite`
+- Runtime target: CPU only. GPU delegation is not expected for this converted file.
+- Input: `float32` tensor in NCHW layout, shape `[1, 3, 448, 448]`
+- Output: ImageNet-1K logits, shape `[1, 1000]`
+- Converted artifact size: 1.14 GiB
+- Weight storage: `inline`
+
+## Model Details
+
+- **Model Type:** Image classification / feature backbone
+- **Model Stats:**
+  - Params (M): 305.1
+  - GMACs: 362.3
+  - Activations (M): 689.9
+  - Image size: 448 x 448
+- **Papers:**
+  - EVA-02: A Visual Representation for Neon Genesis: https://arxiv.org/abs/2303.11331
+  - EVA-CLIP: Improved Training Techniques for CLIP at Scale: https://arxiv.org/abs/2303.15389
+- **Original:**
+  - https://github.com/baaivision/EVA
+  - https://huggingface.co/Yuxin-CV/EVA-02
+- **Pretrain Dataset:** ImageNet-22k
+- **Dataset:** ImageNet-1k
+
+## Citation
+
+```bibtex
+@article{EVA02,
+  title={EVA-02: A Visual Representation for Neon Genesis},
+  author={Fang, Yuxin and Sun, Quan and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
+  journal={arXiv preprint arXiv:2303.11331},
+  year={2023}
+}
+```
+```bibtex
+@article{EVA-CLIP,
+  title={EVA-02: A Visual Representation for Neon Genesis},
+  author={Sun, Quan and Fang, Yuxin and Wu, Ledell and Wang, Xinlong and Cao, Yue},
+  journal={arXiv preprint arXiv:2303.15389},
+  year={2023}
+}
+```
+```bibtex
+@misc{rw2019timm,
+  author = {Ross Wightman},
+  title = {PyTorch Image Models},
+  year = {2019},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  doi = {10.5281/zenodo.4414861},
+  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
+}
+```

model.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fe62785356483deac9ca1e6da8c91266d8443fcd163c1eff0d8a4a772c26d5
+size 1220391008