software-mansion/react-native-executorch-hammer-2.1

Apply the model card standard

Apply the model card standard

fix: MLX configs declare cc-by-nc-4.0, matching the XNNPACK configs and card

Add MLX int4 variants for 0.5B, 1.5B and 3B

Stop restating quantized, and drop the unused default

Correct the published metadata

Re-export with consistent stop tokens (0_5b first) (#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 hammer2_1_0_5B_8da4w.pte

Upload hammer2_1_1_5B_8da4w.pte

Upload hammer2_1_3B_8da4w.pte

Fix invalid JSON in config.json

Update README.md

Upload hammer2_1_3B_8da4w.pte

Update README.md

Update README.md

Upload hammer2_1_3B_bf16.pte

Upload hammer2_1_1_5B_8da4w.pte

Upload hammer2_1_1_5B_bf16.pte

Upload hammer2_1_0_5B_8da4w.pte

Update hammer-2.1-3B/quantized/config.json

Update hammer-2.1-3B/original/config.json

Upload hammer2_1_0_5B_bf16.pte

Update hammer-2.1-3B/quantized/config.json

Update hammer-2.1-3B/original/config.json

Update hammer-2.1-1.5B/quantized/config.json

Update hammer-2.1-1.5B/original/config.json

Update hammer-2.1-0.5B/quantized/config.json

Update hammer-2.1-0.5B/original/config.json

Create hammer-2.1-3B/original/config.json

Create hammer-2.1-3B/quantized/config.json

Create hammer-2.1-1.5B/quantized/config.json

Create hammer-2.1-1.5B/original/config.json

Create hammer-2.1-0.5B/quantized/config.json

Create hammer-2.1-0.5B/original/config.json

Delete original/config.json

Delete original/hammer2_1_bf16.pte

Create config.json

Update README.md

Update original/config.json

Upload hammer2_1_bf16.pte

Create original/config.json

Upload 2 files