lmstudio-community
/

Qwen3-30B-A3B-Thinking-2507-MLX-8bit

Text Generation

8-bit precision

Model card Files Files and versions

rugvedS07 commited on Jul 30

Commit

0a54d3d

·

verified ·

1 Parent(s): dce3d47

Update chat_template.jinja

Files changed (1) hide show

chat_template.jinja +1 -1

chat_template.jinja CHANGED Viewed

@@ -82,5 +82,5 @@
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n<think>\n' }}
 {%- endif %}

     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
 {%- endif %}