Update README.md
Browse files
README.md
CHANGED
|
@@ -28,10 +28,18 @@ F16 is full precision.
|
|
| 28 |
|
| 29 |
Context Length: 32 K + 8K output generation.
|
| 30 |
|
| 31 |
-
NOTE
|
| 32 |
|
| 33 |
If you are having issues with Jinja "auto template", use CHATML template.
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
Reasoning is ON by default in this model, and model will auto-generate "think" block(s).
|
| 36 |
|
| 37 |
For benchmarks, usage info, settings please see org model card here:
|
|
|
|
| 28 |
|
| 29 |
Context Length: 32 K + 8K output generation.
|
| 30 |
|
| 31 |
+
<B>NOTE - Jinja Template / Template to Use with this Model:</B>
|
| 32 |
|
| 33 |
If you are having issues with Jinja "auto template", use CHATML template.
|
| 34 |
|
| 35 |
+
OR (LMSTUDIO users / option)
|
| 36 |
+
|
| 37 |
+
Update the Jinja Template (go to this site, template-> copy the "Jinja template" and then paste.)
|
| 38 |
+
|
| 39 |
+
[ https://lmstudio.ai/neil/qwen3-thinking ]
|
| 40 |
+
|
| 41 |
+
<B>Other Notes:</B>
|
| 42 |
+
|
| 43 |
Reasoning is ON by default in this model, and model will auto-generate "think" block(s).
|
| 44 |
|
| 45 |
For benchmarks, usage info, settings please see org model card here:
|