Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,76 @@
+---
+license: other
+tags:
+- executorch
+- xnnpack
+- pte
+- on-device
+- image-text-to-text
+base_model:
+- LiquidAI/LFM2.5-VL-450M
+---
+# LFM2.5-VL-450M — ExecuTorch
+
+`lfm2_5_vl_450m_xnnpack.pte` (2.07 GB)
+
+- **Source**: LiquidAI/LFM2.5-VL-450M — SigLIP 2 vision tower (768 wide, 12 layers) and an
+  LFM2 decoder (1024 wide, 16 layers)
+- **License**: LFM Open License v1.0
+- **Input**: a 512×512 tile as `[1, 1024, 768]` patches plus `[1, 1024]` attention mask,
+  and token ids for the words around it
+- **Output**: logits over the 65,536-token vocabulary
+
+One file, three entry points — the shape ExecuTorch's multimodal runner asks for:
+
+| method | in | out |
+|---|---|---|
+| `vision_encoder` | patches, mask | `[1, 256, 1024]` rows in the decoder's embedding space |
+| `token_embeddings` | token ids | embeddings |
+| `text_model` | embeddings, positions | logits |
+
+A decoder that only takes token ids cannot be told about a picture. Splitting a
+vision-language model into a vision `.pte` and a text `.pte` runs aground there;
+`MultimodalPrefiller::load` asks one module for `token_embeddings` and `text_model` and uses
+`vision_encoder` if it finds it.
+
+## Verification (Mac arm64, 2026-08-21)
+
+Greedy, through the three methods, on photographs from `convert/calib_images`:
+
+| picture | answer |
+|---|---|
+| a London street | "A bustling street scene with people walking, outdoor seating, and various storefronts, including a prominent Pizza Express." |
+| a man with a dog | "A man with a dog is standing in front of a stack of logs with a water tower in the background." |
+| a studio portrait | "A man in a gray long-sleeve shirt poses against a white background…" |
+
+The shop sign is read correctly, which is the check that matters: a caption that fits any
+street would not tell you the vision half was wired up right.
+
+The vision encoder alone agrees with the untouched model at **corr 0.99996** (XNNPACK fp32,
+against `get_image_features` on real imagery).
+
+## Square the picture first
+
+The processor picks a tile grid from the aspect ratio — a 768×477 photograph becomes one
+24×40 tile, a 1280×960 one becomes seven — and this graph takes 32×32. Centre-crop to a
+square before the processor sees it and every picture becomes exactly one tile. Feeding a
+stretched square instead is visible in the output: asked about a squashed street, the model
+called the scene "distorted and warped", which was a fair description of what it had been
+given.
+
+```bash
+python convert/run_lfm2_vl.py <image> "What is in this picture?"
+```
+
+## Conversion
+
+`convert/export_lfm2_vl_bundle.py`. Two things needed re-authoring:
+
+- **SigLIP 2 reads its grid out of a tensor** to size the position embeddings, which
+  `torch.export` cannot follow. The grid is fixed here, so the resize is computed once and
+  the constant handed to a replacement forward.
+- **The projector wants the grid back.** The tower returns a flat run of patches; the
+  projector's pixel-unshuffle trades resolution for channels and needs to know which patches
+  are neighbours.
+
+(conversion scripts: [executorch-models](https://github.com/john-rocky/executorch-models))