Update README.md
Browse files
README.md
CHANGED
|
@@ -31,7 +31,7 @@ F16 is full precision.
|
|
| 31 |
|
| 32 |
Context Length: 32 K + 8K output generation. (can be extended to 128k)
|
| 33 |
|
| 34 |
-
NOTE - Jinja Template / Template to Use with this Model
|
| 35 |
|
| 36 |
If you are having issues with Jinja "auto template", use CHATML template.
|
| 37 |
|
|
@@ -41,6 +41,8 @@ Update the Jinja Template (go to this site, template-> copy the "Jinja template"
|
|
| 41 |
|
| 42 |
[ https://lmstudio.ai/neil/qwen3-thinking ]
|
| 43 |
|
|
|
|
|
|
|
| 44 |
Reasoning is ON by default in this model, and model will auto-generate "think" block(s).
|
| 45 |
|
| 46 |
For benchmarks, usage info, settings please see org model card here:
|
|
|
|
| 31 |
|
| 32 |
Context Length: 32 K + 8K output generation. (can be extended to 128k)
|
| 33 |
|
| 34 |
+
<B>NOTE - Jinja Template / Template to Use with this Model:</B>
|
| 35 |
|
| 36 |
If you are having issues with Jinja "auto template", use CHATML template.
|
| 37 |
|
|
|
|
| 41 |
|
| 42 |
[ https://lmstudio.ai/neil/qwen3-thinking ]
|
| 43 |
|
| 44 |
+
<B>Other Notes:</B>
|
| 45 |
+
|
| 46 |
Reasoning is ON by default in this model, and model will auto-generate "think" block(s).
|
| 47 |
|
| 48 |
For benchmarks, usage info, settings please see org model card here:
|