Update README.md
Browse files
README.md
CHANGED
|
@@ -89,6 +89,24 @@ Please refer to our GitHub repository for installation instructions, examples, a
|
|
| 89 |
|
| 90 |
👉 **[https://github.com/MiroMindAI/MiroThinker](https://github.com/MiroMindAI/MiroThinker)**
|
| 91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
## License
|
| 93 |
|
| 94 |
MiroThinker v1.0 is released under the MIT License.
|
|
|
|
| 89 |
|
| 90 |
👉 **[https://github.com/MiroMindAI/MiroThinker](https://github.com/MiroMindAI/MiroThinker)**
|
| 91 |
|
| 92 |
+
## Local Deployment
|
| 93 |
+
|
| 94 |
+
It is recommended to use SGLang for deploying the model:
|
| 95 |
+
|
| 96 |
+
```shell
|
| 97 |
+
python -m sglang.launch_server --model-path miromind-ai/MiroThinker-v1.0-8B --host 0.0.0.0 --port 1234
|
| 98 |
+
```
|
| 99 |
+
|
| 100 |
+
For optimal performance in agentic tasks, we recommend the following inference parameters:
|
| 101 |
+
|
| 102 |
+
```
|
| 103 |
+
temperature: 1.0
|
| 104 |
+
top_p: 0.95
|
| 105 |
+
repetition_penalty: 1.05
|
| 106 |
+
max_context_length: 262144
|
| 107 |
+
max_tokens: 16384
|
| 108 |
+
```
|
| 109 |
+
|
| 110 |
## License
|
| 111 |
|
| 112 |
MiroThinker v1.0 is released under the MIT License.
|