software-mansion/react-native-executorch-clip-vit-base-patch32

Declare the int8 Core ML variant

Add int8 Core ML variant (embedding table quantized)

Core ML: accept a sequence length of 1

Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Nest the per-component methods

Correct the published metadata

Add Vulkan fp16 variants (image and text)

MLX int8 image tower; drop MLX fp32 and XNNPACK int8

Add the missing coreml/config.json; drop the image fp32 variant

Core ML: pin compute_unit=CPU_ONLY, drop the fp32 variant

Add clip text coreml export (CPU_AND_NE, ExecuTorch 1.4.1)

Add clip text coreml export (CPU_AND_NE, ExecuTorch 1.4.1)

Add export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Add coreml export (ExecuTorch 1.4.1)

Update .pte files for v0.10.0

Re-export text embeddings with get_dynamic_dims_forward dynamic-shape contract

Re-export text encoder with get_dynamic_dims (variable-length input bounds)

fix(v0.9.0): rename vision→image; restore text encoder from v0.8.0

Add stub root config.json for HF download counter

Add spec-compliant config.json files

Add spec-compliant config.json files

Remove old-layout metadata orphaned by MODEL_SPEC.md restructure

Restructure to MODEL_SPEC.md convention

Fix README

Update README

Update models. Add quantized models.

Update .gitattributes

Upload tokenizer.json

Upload config.json

Upload 2 files

Update README.md

initial commit