software-mansion/react-native-executorch-llama-3.2

Apply the model card standard

Add MLX int4 variants for 1B and 3B

Apply the model card standard

Apply the model card standard

Remove the QLoRA variants, unsupported since v0.10

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

Add config.json for QLoRA variants

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

Fix invalid JSON in config.json

Update README.md

Update README.md

update non-quantized llama models to include context len in metadata

update README

update README

update models to work with v0.6.0 runtime

Update tokenizer_config

Upload tokenizer_config.json

Replace .bin tokenizers with .json

Add config.json to repository root

Add config.json to each of the models

Update README.md

Upload llama3_2_bf16.pte

Upload llama3_2_3B_bf16.pte

Delete llama3_2

Update README.md

Delete llama-3.2-3B/spinquant/README.md

Delete llama-3.2-3B/original/README.md

Delete llama-3.2-3B/QLoRA/README.md

Delete llama-3.2-1B/README.md

Delete llama-3.2-1B/spinquant/README.md

Delete llama-3.2-1B/QLoRA/README.md

Delete llama-3.2-1B/original/README.md

Delete llama-3.2-3B/README.md

Rename llama-3.2-3B/original/llama3_2_bf16.pte to llama-3.2-3B/original/llama3_2_3B_bf16.pte

Upload 2 files

Upload 2 files

Upload 2 files

Create original/README.md

Create spinquant/README.md

Create QLoRA/README.md

Create llama-3.2-3B/README.md

Upload 2 files