Name the model MBHS
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
- extractive-qa
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# Find in Page AI
|
| 16 |
|
| 17 |
The answer model of [Find in Page AI](https://github.com/Vanyattka/find-in-page-ai), a browser extension that answers questions about the page you are reading, locally on WebGPU. This is [Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) with a LoRA (rank 16, all linear layers) trained for the extension's answer format, in the same ONNX files as [onnx-community/Qwen3.5-0.8B-Text-ONNX](https://huggingface.co/onnx-community/Qwen3.5-0.8B-Text-ONNX): `onnx/model_q4f16.onnx` (WebGPU with shader-f16) and `onnx/model_q4.onnx`. The LoRA adapter is in `lora/`.
|
| 18 |
|
|
|
|
| 12 |
- extractive-qa
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# MBHS — the answer model of Find in Page AI (Qwen3.5-0.8B, pilot fine-tune)
|
| 16 |
|
| 17 |
The answer model of [Find in Page AI](https://github.com/Vanyattka/find-in-page-ai), a browser extension that answers questions about the page you are reading, locally on WebGPU. This is [Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B) with a LoRA (rank 16, all linear layers) trained for the extension's answer format, in the same ONNX files as [onnx-community/Qwen3.5-0.8B-Text-ONNX](https://huggingface.co/onnx-community/Qwen3.5-0.8B-Text-ONNX): `onnx/model_q4f16.onnx` (WebGPU with shader-f16) and `onnx/model_q4.onnx`. The LoRA adapter is in `lora/`.
|
| 18 |
|