Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+fp16/model.pte filter=lfs diff=lfs merge=lfs -text
+int4/model.pte filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,26 @@
+---
+library_name: executorch
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+tags:
+  - executorch
+  - on-device
+  - mobile
+---
+
+# qwen-0.5b (ExecuTorch)
+
+This model is a derivative of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) converted to **ExecuTorch (.pte)** format for mobile/edge deployment.
+
+## Variants Available
+
+| Folder | Quantization | Size | Description |
+|---|---|---|---|
+| `int4/` | 8-bit Act / 4-bit Wgt | Small | **Best for Mobile** |
+| `fp16/` | Float16 | Large | High Precision |
+
+## License & Terms
+
+This model derivative is subject to the original model's license terms:
+- **Source:** [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
+
+Please check the source model card for license details (likely Apache 2.0 or Llama Community).

fp16/model.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70787ab993fab9b9299e8d5dbe09ff8d9969b54aa42bdfff54dd7ac8a608bd3
+size 2521307904

int4/model.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a7c29df20a4224fa91e83c5ba0c18e4b2b5a5ea3822a7c965fa2ee86a26d39
+size 415595264