Hugging Face's logo

Omdano
/
INT8-H16P

PyTorch
dinov3_vit
Model card Files
xet
Community
INT8-H16P

Commit History

Re-quantize with float16 for T4 GPU compatibility
c68d969
verified

Omdano commited on

Remove model.safetensors - use pytorch_model.bin with INT8 weights
29acac0
verified

Omdano commited on

Add back TorchAO INT8 quantization_config for proper loading
1209faf
verified

Omdano commited on

Remove quantization_config to avoid BitsAndBytes imports
c7f451a
verified

Omdano commited on

Upload folder using huggingface_hub
e020402
verified

Omdano commited on

Upload README.md with huggingface_hub
8eada2c
verified

Omdano commited on

Upload folder using huggingface_hub
8bf2e5c
verified

Omdano commited on

initial commit
4f8176a
verified

Omdano commited on