Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+license: apache-2.0
+base_model: Hcompany/Holo2-4B
+pipeline_tag: image-text-to-text
+tags:
+- core-ai
+- coreml
+- on-device
+- ios
+- iphone
+- vision-language
+- gui-grounding
+- computer-use
+- qwen3-vl
+language:
+- en
+---
+
+# Holo2-4B — Core AI (on-device, iPhone) · GUI-grounding VLM
+
+[Hcompany/Holo2-4B](https://huggingface.co/Hcompany/Holo2-4B) converted to Apple **Core AI**
+for on-device inference, served by the **CoreAIChat** app.
+
+Holo2 is H Company's **computer-use / GUI-grounding** vision-language model: given a screenshot
+and an instruction ("click the submit button"), it predicts the **click coordinates / locates the
+UI element**. Built on the **Qwen3-VL-4B** backbone, so it rides the Core AI zoo's existing
+Qwen3-VL pipeline. The zoo's **first GUI-grounding / computer-use model**.
+
+## Contents (`gpu-pipelined/`)
+- `holo2_4b_decode_int8lin_s1/` — the **decode** bundle (static query=1, per-block-32 int8 linear
+  body; rides Apple's `coreai-pipelined` GPU engine, specializes on-device — no AOT needed). ~4.4 GB.
+- `holo2_4b_vision/` — the fixed-grid **vision encoder** `.aimodel` (fp16): `patches [784,1536]
+  -> (image_embeds [196,2560], deepstack [3,196,2560])`. Run once per image. ~0.8 GB.
+
+## Parity (vs fp32 HF oracle, Core AI GPU engine)
+- **Vision:** image-embeds cos **0.999983**, deepstack cos **0.999989**.
+- **Decoder (int8lin):** teacher-forced S=1 sweep **4/4**, **16/16** decode steps token-exact,
+  HF-seeded decode match. All PASS.
+
+## Use
+Install **CoreAIChat**, pick **Holo2 4B**, attach a screenshot, and ask where an element is /
+what to click — it grounds the instruction to the image.
+
+## License
+Apache-2.0, inherited from the base model
+[Hcompany/Holo2-4B](https://huggingface.co/Hcompany/Holo2-4B). See `LICENSE`.