software-mansion/react-native-executorch-gemma-4

Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Use min/max dynamic shape bounds for forward inputs/outputs

Backfill constant metadata method values in config.json from .pte

Update README.md

Delete e2b/mlx/tokenizer_config.json

Delete e2b/mlx/tokenizer.json

Create config.json

Delete e2b/xnnpack/tokenizer_config.json

Delete e2b/xnnpack/tokenizer.json

Delete e2b/vulkan/tokenizer_config.json

Delete e2b/vulkan/tokenizer.json

Update README.md

Upload folder using huggingface_hub

Create README.md

Delete e2b/mlx/config.json

Rename e2b/mlx/tokenizer_config (1).json to e2b/mlx/tokenizer_config.json

Rename e2b/mlx/tokenizer (4).json to e2b/mlx/tokenizer.json

Upload 2 files

Rename e2b/mlx/gemma4_e2b_mlx_int4_labs_v5.pte to e2b/mlx/gemma4_e2b_mlx_int4.pte

Upload gemma4_e2b_mlx_int4_labs_v5.pte

Create mlx/config.json

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit