Instructions to use MHanzl/FGVC-tf_efficientnet_b3.ap_in1k-CrossEntropyLoss-light-exp2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MHanzl/FGVC-tf_efficientnet_b3.ap_in1k-CrossEntropyLoss-light-exp2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MHanzl/FGVC-tf_efficientnet_b3.ap_in1k-CrossEntropyLoss-light-exp2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from MHanzl/FGVC-tf_efficientnet_b3.ap_in1k-CrossEntropyLoss-light-exp2: direct link, hf CLI and curl.
- Browser
- Download file 44.5 MB
-
https://huggingface.co/MHanzl/FGVC-tf_efficientnet_b3.ap_in1k-CrossEntropyLoss-light-exp2/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://MHanzl/FGVC-tf_efficientnet_b3.ap_in1k-CrossEntropyLoss-light-exp2/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/MHanzl/FGVC-tf_efficientnet_b3.ap_in1k-CrossEntropyLoss-light-exp2/resolve/main/pytorch_model.bin
44.5 MB
- Xet hash:
- 8fc6939297aea281d1de6f638b420d07bdbae6420ef3425669963d2151293adf
- Size of remote file:
- 44.5 MB
- SHA256:
- 36c9edd0597db2f66620288a139f033d991cddc70635d63dc9d3e43891895b0c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.