Add model card

README.md

@@ -0,0 +1,82 @@
+---
+base_model: typhoon-ai/typhoon-ocr1.5-2b
+base_model_relation: quantized
+license: apache-2.0
+language:
+  - en
+  - th
+pipeline_tag: image-text-to-text
+library_name: llama.cpp
+tags:
+  - gguf
+  - imatrix
+  - OCR
+  - vision-language
+  - document-understanding
+  - multimodal
+  - llama.cpp
+---
+
+# typhoon-ocr1.5-2b GGUF
+
+GGUF quantization of [typhoon-ai/typhoon-ocr1.5-2b](https://huggingface.co/typhoon-ai/typhoon-ocr1.5-2b),
+a Thai/English document-OCR vision-language model built on Qwen3-VL-2B-Instruct.
+
+This is a **vision-language model**: you need both the model file and the `mmproj`
+(multimodal projector) file. The model file alone will load, but it will not see images.
+
+## Files
+
+| File | Size | Notes |
+| --- | --- | --- |
+| `typhoon-ocr1.5-2b-Q4_K_M-imat.gguf` | 1.03 GiB | Language model, Q4_K_M with importance matrix |
+| `typhoon-ocr1.5-2b-mmproj-Q8_0.gguf` | 424 MiB | Vision encoder / projector — **required** |
+
+The Q4_K_M weights were quantized with an importance matrix (imatrix) computed from a
+calibration set, which recovers some of the quality lost at 4 bits compared to a plain
+Q4_K_M of the same size.
+
+## Usage
+
+### llama-server (OpenAI-compatible API)
+
+```bash
+llama-server \
+  -m typhoon-ocr1.5-2b-Q4_K_M-imat.gguf \
+  --mmproj typhoon-ocr1.5-2b-mmproj-Q8_0.gguf \
+  -c 8192 --host 0.0.0.0 --port 8080
+```
+
+Then post an image to `/v1/chat/completions` the usual way:
+
+```bash
+curl http://localhost:8080/v1/chat/completions \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "messages": [{
+      "role": "user",
+      "content": [
+        {"type": "image_url", "image_url": {"url": "data:image/png;base64,<BASE64>"}},
+        {"type": "text", "text": "Extract all text from this document as Markdown."}
+      ]
+    }]
+  }'
+```
+
+### llama-mtmd-cli (one-shot)
+
+```bash
+llama-mtmd-cli \
+  -m typhoon-ocr1.5-2b-Q4_K_M-imat.gguf \
+  --mmproj typhoon-ocr1.5-2b-mmproj-Q8_0.gguf \
+  --image page.png \
+  -p "Extract all text from this document as Markdown."
+```
+
+Use a recent llama.cpp build — Qwen3-VL support landed relatively late.
+
+## License
+
+Apache 2.0, inherited from the base model. See the
+[base model card](https://huggingface.co/typhoon-ai/typhoon-ocr1.5-2b) for the model's
+intended use and limitations.