Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Re-export the 8da4w text variants at the sweep's group size (#1)

Add LFM2.5-VL 1.6B MLX int8 (8w) build

Update chat template for strict monotonicity and tool support

Add LFM2.5-VL 1.6B vulkan (8da4w) build

Add LFM2.5-VL 450M vulkan (8da4w) build

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

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

Rename vl_1_6b/mlx/lfm2_5_vl_1_6b_fullmlx_allbf16_dyn.pte to vl_1_6b/mlx/lfm_2_5_vl_1_6b_mlx_int4.pte

Upload lfm2_5_vl_1_6b_fullmlx_allbf16_dyn.pte

Rename vl_450m/mlx/lfm2_5_vl_450m_fullmlx_allbf16_dyn.pte to vl_450m/mlx/lfm_2_5_vl_450m_mlx_int4.pte

Upload lfm2_5_vl_450m_fullmlx_allbf16_dyn.pte

Create mlx/config.json

Create mlx/config.json

Rename 1_2b/mlx/lfm2_5_1_2b_mlx_4w_v2.pte to 1_2b/mlx/lfm_2_5_1_2b_mlx_int4.pte

Upload lfm2_5_1_2b_mlx_4w_v2.pte

Rename 350m/mlx/lfm2_5_350m_mlx_4w_v2.pte to 350m/mlx/lfm_2_5_350m_mlx_int4.pte

Upload lfm2_5_350m_mlx_4w_v2.pte

Create mlx/config.json

Create mlx/config.json

Add stub root config.json for HF download counter

Add spec-compliant config.json files

Refresh lfm-2.5 config.json files for VL/text split

Fix lfm-2.5 layout: distinguish VL from text + colocate tokenizers

Add spec-compliant config.json files

Remove old-layout metadata orphaned by MODEL_SPEC.md restructure

Restructure to MODEL_SPEC.md convention

Upload 2 files

Delete lfm2.5-VL-450M/config.json

Upload lfm2_5_vl_450m_8da4w_xnnpack.pte

Create lfm2.5-VL-450M/config.json

Delete lfm2.5-VL-1.6B/config.json

Create lfm2.5-VL-1.6B/config.json

Update README.md

Create README.md

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit