software-mansion/react-native-executorch-qwen-3

Restore the Qwen3 chat template

Apply the model card standard

Apply the model card standard

Add MLX int4 variants for 0.6B, 1.7B and 4B

Stop restating quantized, and drop the unused default

Correct the published metadata

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 qwen3_4b_8da4w.pte

Upload qwen3_1_7b_8da4w.pte

Upload qwen3_0_6b_8da4w.pte

Fix invalid JSON in config.json

Update README.md

Update README.md

Update qwen-3-4B/quantized/config.json

Update qwen-3-4B/original/config.json

Update qwen-3-1.7B/quantized/config.json

Update qwen-3-1.7B/original/config.json

Update qwen-3-0.6B/quantized/config.json

Update qwen-3-0.6B/original/config.json

Upload qwen3_4b_8da4w.pte

Upload qwen3_4b_bf16.pte

Upload qwen3_1_7b_8da4w.pte

Upload qwen3_1_7b_bf16.pte

Upload qwen3_0_6b_8da4w.pte

Upload qwen3_0_6b_bf16.pte

Create config.json

Create quantized/config.json

Create quantized/config.json

Create quantized/config.json

Create qwen-3-4B/original/config.json

Create qwen-3-1.7B/original/config.json

Create qwen-3-0.6B/original/config.json

Upload 2 files

Update README.md

initial commit