Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,35 @@
|
|
| 24 |
- Structured chain-of-thought (with `<think>…</think>` tags), followed by final answer or solution.
|
| 25 |
- Note: The default template auto-inserts thinking behavior, so you may see only a closing `</think>` tag.
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
## License
|
| 28 |
- Licensed under **Apache-2.0**
|
| 29 |
|
|
|
|
| 24 |
- Structured chain-of-thought (with `<think>…</think>` tags), followed by final answer or solution.
|
| 25 |
- Note: The default template auto-inserts thinking behavior, so you may see only a closing `</think>` tag.
|
| 26 |
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
## How to use
|
| 30 |
+
|
| 31 |
+
> ⚠️ **Hardware requirement:** the model currently runs **only on Qualcomm NPUs** (e.g., Snapdragon-powered AIPC).
|
| 32 |
+
> Apple NPU support is planned next.
|
| 33 |
+
|
| 34 |
+
### 1) Install Nexa-SDK
|
| 35 |
+
|
| 36 |
+
- Download and follow the steps under "Deploy Section" Nexa's model page: [Download Windows arm64 SDK](https://sdk.nexa.ai/model/Qwen3-4B-Thinking-2507)
|
| 37 |
+
- (Other platforms coming soon)
|
| 38 |
+
|
| 39 |
+
### 2) Get an access token
|
| 40 |
+
Create a token in the Model Hub, then log in:
|
| 41 |
+
|
| 42 |
+
```bash
|
| 43 |
+
nexa config set license '<access_token>'
|
| 44 |
+
```
|
| 45 |
+
|
| 46 |
+
### 3) Run the model
|
| 47 |
+
Running:
|
| 48 |
+
|
| 49 |
+
```bash
|
| 50 |
+
nexa infer NexaAI/Qwen3-4B-Thinking-2507-npu
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
---
|
| 54 |
+
|
| 55 |
+
|
| 56 |
## License
|
| 57 |
- Licensed under **Apache-2.0**
|
| 58 |
|