Oct 5, 2025

1. 13:40

   Re-quantize with float16 for T4 GPU compatibility

   Omdano
   Verified signature

   c68d969
2. 12:16

   Remove model.safetensors - use pytorch_model.bin with INT8 weights

   Omdano
   Verified signature

   29acac0
3. 12:11

   Add back TorchAO INT8 quantization_config for proper loading

   Omdano
   Verified signature

   1209faf
4. 12:04

   Remove quantization_config to avoid BitsAndBytes imports

   Omdano
   Verified signature

   c7f451a
5. 11:51

   Upload folder using huggingface_hub

   Omdano
   Verified signature

   e020402
6. 11:14

   Upload README.md with huggingface_hub

   Omdano
   Verified signature

   8eada2c
7. 11:14

   Upload folder using huggingface_hub

   Omdano
   Verified signature

   8bf2e5c
8. 11:11

   initial commit

   Omdano
   Verified signature

   4f8176a