Azaz666
/

FastVLM-1.5B-PYTORCH-INT8

Model card Files Files and versions

FastVLM-1.5B-PYTORCH-INT8 / quant_info.json

Commit History

Replace with per-group INT8 quantization (group_size=128, lossless vs FP16)

0140a80

Azaz666 commited on Mar 27

Upload PyTorch INT8 quantized FastVLM-1.5B (weights + config + eval)

610c048

Azaz666 commited on Mar 27