add in lora

docker-compose.yaml

@@ -12,8 +12,10 @@ services:
       - --chat-template-content-format=string
       - --chat-template=/root/chat_template.jinja
       - --enable-auto-tool-choice
-      - --tool-call-parser=hermes
+      - --tool-call-parser=/root/smol_tool_parser.py
       - --reasoning-parser=deepseek_r1
+      - --enable-lora
+      - --lora-modules=smollm-toolcall=/root/loras/better-tool-call
       #- --max-model-len=131072
       #- --hf-overrides={"rope_scaling":{"type":"yarn","factor":2.0,"original_max_position_embeddings":65536}}
     deploy:
@@ -31,5 +33,6 @@ services:
     volumes:
        - /srv:/root/.cache/huggingface
        - ./chat_template.jinja:/root/chat_template.jinja
-       - ./hermes_tool_parser.py:/usr/local/lib/python3.12/dist-packages/vllm/tool_parsers/hermes_tool_parser.py
+       - ./smol_tool_parser.py:/root/smol_tool_parser.py
+       - ./loras:/root/loras
     network_mode: host