Update README.md
Browse files
README.md
CHANGED
|
@@ -55,6 +55,12 @@ The model adopts an MoE language model, a native-resolution visual encoder (Moon
|
|
| 55 |
|
| 56 |
</div>
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
## Performance
|
| 59 |
|
| 60 |
As an efficient model, Kimi-VL can robustly handle diverse tasks (fine-grained perception, math, college-level problems, OCR, agent, etc) across a broad spectrum of input forms (single-image, multi-image, video, long-document, etc).
|
|
|
|
| 55 |
|
| 56 |
</div>
|
| 57 |
|
| 58 |
+
> [!Note]
|
| 59 |
+
> Recommended parameter settings:
|
| 60 |
+
> - For **Thinking models**, it is recommended to use `Temperature = 0.6`.
|
| 61 |
+
> - For **Instruct models**, it is recommended to use `Temperature = 0.2`.
|
| 62 |
+
|
| 63 |
+
|
| 64 |
## Performance
|
| 65 |
|
| 66 |
As an efficient model, Kimi-VL can robustly handle diverse tasks (fine-grained perception, math, college-level problems, OCR, agent, etc) across a broad spectrum of input forms (single-image, multi-image, video, long-document, etc).
|