software-mansion/react-native-executorch-all-mpnet-base-v2

Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Add the Vulkan int8 weight-only export

Re-export the Vulkan fp16 variant with rank-3 attention

Add a Vulkan fp16 variant

Update .pte files for v0.10.0

Re-export text embeddings with get_dynamic_dims_forward dynamic-shape contract

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

Upload all-mpnet-base-v2_xnnpack.pte

Upload all-mpnet-base-v2_xnnpack.pte

Upload tokenizer.json

Upload 2 files (#1)

Change max_length

Rename all-mpnet-base-v2.pte to all-mpnet-base-v2_xnnpack.pte

Update README.md

Update config.json

Update config.json

Create config.json

Delete all-mpnet-base-v2.py

Upload 3 files

Upload 3 files

initial commit