add qwen3 no thinking

apps/librechat/release.yaml

@@ -66,7 +66,7 @@ spec:
                 default: [
                   "DeepSeek-R1-0528-Qwen3-8B-GGUF",
                   "Qwen3-8B-GGUF",
-                  "Qwen3-8B-GGUF-Q6_K"
+                  "Qwen3-8B-GGUF-no-thinking"
                 ]
               titleConvo: true
               titleModel: "current_model"

apps/llama/configmap.yaml

@@ -1,26 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  namespace: llama
-  name: llama-swap
-data:
-  config.yaml: |
-    models:
-      "DeepSeek-R1-0528-Qwen3-8B-GGUF":
-        cmd: |
-          /app/llama-server
-          -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M
-          -ngl 37 -c 16384
-          --port ${PORT}
-      "Qwen3-8B-GGUF":
-        cmd: |
-          /app/llama-server
-          -hf unsloth/Qwen3-8B-GGUF:Q4_K_M
-          -ngl 37 -c 16384
-          --port ${PORT}
-      "Qwen3-8B-GGUF-Q6_K":
-        cmd: |
-          /app/llama-server
-          -hf unsloth/Qwen3-8B-GGUF:Q6_K
-          -ngl 37 -c 16384
-          --port ${PORT}

apps/llama/configs/config.yaml

@@ -0,0 +1,20 @@
+models:
+  "DeepSeek-R1-0528-Qwen3-8B-GGUF":
+    cmd: |
+      /app/llama-server
+      -hf unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M
+      -ngl 37 -c 16384
+      --port ${PORT}
+  "Qwen3-8B-GGUF":
+    cmd: |
+      /app/llama-server
+      -hf unsloth/Qwen3-8B-GGUF:Q4_K_M
+      -ngl 37 -c 16384
+      --port ${PORT}
+  "Qwen3-8B-GGUF-no-thinking":
+    cmd: |
+      /app/llama-server
+      -hf unsloth/Qwen3-8B-GGUF:Q4_K_M
+      -ngl 37 -c 16384
+      --jinja --chat-template-file /config/qwen_nothink_chat_template.jinja
+      --port ${PORT}

apps/llama/configs/qwen_nothink_chat_template.jinja

@@ -0,0 +1,101 @@
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- if ns.is_first_sp %}
+            {%- set ns.system_prompt = ns.system_prompt + message['content'] %}
+            {%- set ns.is_first_sp = false %}
+        {%- else %}
+            {%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}
+{%- if tools is defined and tools is not none %}
+    {%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
+    {%- for tool in tools %}
+        {%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
+    {%- endfor %}
+    {%- if ns.system_prompt|length != 0 %}
+        {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
+    {%- else %}
+        {%- set ns.system_prompt = tool_ns.text %}
+    {%- endif %}
+{%- endif %}
+{{- bos_token }}
+{{- '/no_think' + ns.system_prompt }}
+{%- set last_index = (messages|length - 1) %}
+{%- for message in messages %}
+    {%- set content = message['content'] %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_first = false -%}
+        {%- set ns.is_last_user = true -%}
+        {%- if loop.index0 == last_index %}
+            {{- '<｜User｜>' + content }}
+        {%- else %}
+            {{- '<｜User｜>' + content + '<｜Assistant｜>'}}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' %}
+        {%- if '</think>' in content %}
+            {%- set content = (content.split('</think>')|last) %}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>'}}
+        {%- endif %}
+        {%- set ns.is_first = false %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_output_first = true %}
+        {%- for tool in message['tool_calls'] %}
+            {%- set arguments = tool['function']['arguments'] %}
+            {%- if arguments is not string %}
+                {%- set arguments = arguments|tojson %}
+            {%- endif %}
+            {%- if not ns.is_first %}
+                {%- if content is none %}
+                    {{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                }
+                {%- else %}
+                    {{- content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                {%- endif %}
+                {%- set ns.is_first = true -%}
+            {%- else %}
+                {{- '\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+            {%- endif %}
+        {%- endfor %}
+        {{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}
+            {%- set ns.is_tool = false -%}
+        {%- else %}
+            {{- content + '<｜end▁of▁sentence｜>'}}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set ns.is_last_user = false -%}
+        {%- set ns.is_tool = true -%}
+        {%- if ns.is_output_first %}
+            {{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
+            {%- set ns.is_output_first = false %}
+        {%- else %}
+            {{- '\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
+        {%- endif %}
+    {%- endif %}
+{%- endfor -%}
+{%- if ns.is_tool %}
+    {{- '<｜tool▁outputs▁end｜>'}}
+{%- endif %}
+{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}
+{%- if add_generation_prompt and not ns.is_tool %}
+    {{- '<｜Assistant｜>'}}
+{%- endif %}

apps/llama/kustomization.yaml

@@ -7,4 +7,9 @@ resources:
   - ingress.yaml
   - pvc.yaml
   - deployment.yaml
-  - configmap.yaml
+configMapGenerator:
+  - name: llama-swap
+    namespace: llama
+    files:
+      - config.yaml=configs/config.yaml
+      - qwen_nothink_chat_template.jinja=configs/qwen_nothink_chat_template.jinja