zen314
/

mal-ai-models

Model card Files Files and versions

Commit History

Replace FP32 model with INT8 weight-only quantized version (1.6GB → 416MB)

60bfb01
verified

salmonswan commited on Feb 22

Upload medsiglip_vision_int8.tflite with huggingface_hub

a9e2c27
verified

salmonswan commited on Feb 21

Upload slide_text_embeddings.bin with huggingface_hub

2bb5236
verified

salmonswan commited on Feb 21

Upload via_text_embeddings.bin with huggingface_hub

6611c70
verified

salmonswan commited on Feb 21

initial commit

0d1249f
verified

salmonswan commited on Feb 21