software-mansion/react-native-executorch-smolLm-2

Apply the model card standard

Apply the model card standard

Add MLX int8 variants for 135M, 360M and 1.7B

Stop restating quantized, and drop the unused default

Correct the published metadata

Ship one int8 (8da8w) variant per size (#1)

Update chat template for strict monotonicity and tool support

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

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

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 smolLm2_1_7B_8da4w.pte

Upload smolLm2_135M_8da4w.pte

Upload smolLm2_360M_8da4w.pte

Fix invalid JSON in config.json

Update README.md

Update README.md

Update smolLm-2-135M/quantized/config.json

Update smolLm-2-135M/original/config.json

Upload smolLm2_1_7B_8da4w.pte

Update smolLm-2-1.7B/quantized/config.json

Update smolLm-2-1.7B/original/config.json

Update smolLm-2-360M/quantized/config.json

Update smolLm-2-360M/original/config.json

Upload smolLm2_360M_8da4w.pte

Upload smolLm2_360M_bf16.pte

Upload smolLm2_135M_8da4w.pte

Upload smolLm2_135M_bf16.pte

Upload smolLm2_1_7B_bf16.pte

Create config.json

Create quantized/config.json

Create smolLm-2-1.7B/original/config.json

Create quantized/config.json

Create smolLm-2-360M/original/config.json

Create quantized/config.json

Create smolLm-2-135M/original/config.json

Delete original/config.json

Delete original/smolLm2_bf16.pte

Update README.md

Update original/config.json

Upload smolLm2_bf16.pte

Create original/config.json

Upload 2 files

initial commit