FluidInference
/

clef-vision-0.8b-coreml

Image-Text-to-Text

image-classification

Model card Files Files and versions

clef-vision-0.8b-coreml / Vision_P784

800 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

alexwengg's picture

add fp16 vision (default), ANE-layout fp16 vision, fp16 heads for all buckets; manifest variants + compute-unit guidance

448732d verified 4 days ago

VisionTowerANE_fp16.mlpackage
add fp16 vision (default), ANE-layout fp16 vision, fp16 heads for all buckets; manifest variants + compute-unit guidance 4 days ago
VisionTower_fp16.mlpackage
add fp16 vision (default), ANE-layout fp16 vision, fp16 heads for all buckets; manifest variants + compute-unit guidance 4 days ago
VisionTower_fp32.mlpackage
clef-vision-0.8b: Core ML packages (vision fp32, LM L512/L1024/L2048 fp16, head fp32), embeddings, tokenizer, card 4 days ago
config.json

140 Bytes
clef-vision-0.8b: Core ML packages (vision fp32, LM L512/L1024/L2048 fp16, head fp32), embeddings, tokenizer, card 4 days ago
pos_embed.f32

7.08 MB
xet

add vision pos_embed table, head buckets L512/L2048, manifest text_config_summary 4 days ago