Views
No views yet
tf_lite_prefill_decode) quantization recipe: dynamic_wi8_afp32weight_only_wi8_afp32quantizedlitertlm_medgemma-1.5-4b-it-fp8.litertlm: LiteRT-LM bundle for MedGemma 1.5 4B IT..litertlm artifacts.1from huggingface_hub import hf_hub_download
2
3path = hf_hub_download(
4 repo_id="ai4med-id/medgemma-1.5-4b-it-litertlm",
5 filename="litertlm_medgemma-1.5-4b-it-fp8.litertlm",
6)
7print(path)google/medgemma-1.5-4b-it.litertlm)128, 256, 5124096