Update Dockerfile

Dockerfile

@@ -10,17 +10,18 @@ RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/ge
 RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/mtp-gemma-4-E2B-it.gguf" -O /models/mtp-gemma-4-E2B-it.gguf
 RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/mmproj-F16.gguf" -O /models/gemma-4-E2B-it-mmproj.gguf
 
-# --- NEW MODEL: Gemma 3 270M IT Q8_0 (Swapped from F16) ---
+# --- MODEL 2: Gemma 3 270M IT Q8_0 ---
 RUN wget "https://huggingface.co/unsloth/gemma-3-270m-it-GGUF/resolve/main/gemma-3-270m-it-Q8_0.gguf" -O /models/gemma-3-270m-it-Q8_0.gguf
 
-# --- MODEL 2: Gemma 3 1B Model ---
+# --- MODEL 3: Gemma 3 1B Model ---
 RUN wget "https://huggingface.co/MaziyarPanahi/gemma-3-1b-it-GGUF/resolve/main/gemma-3-1b-it.Q3_K_M.gguf" -O /models/gemma-3-1b-it.Q3_K_M.gguf
 
-# --- MODEL 3: Ornith 1.0 9B Model ---
+# --- MODEL 4: Ornith 1.0 9B Model ---
 RUN wget "https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B-GGUF/resolve/main/ornith-1.0-9b-Q4_K_M.gguf" -O /models/ornith-1.0-9b-Q4_K_M.gguf
 
-# --- NEW MODEL 4: Qwen 3.5 0.8B Model ---
-RUN wget "https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF/resolve/main/Qwen3.5-0.8B-Q4_K_M.gguf?download=true" -O /models/qwen-3.5-0.8b.gguf
+# --- MODEL 5: Qwen 3.5 0.8B Multimodal (Vision) ---
+RUN wget "https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF/resolve/main/Qwen3.5-0.8B-Q4_0.gguf" -O /models/Qwen3.5-0.8B-Q4_0.gguf
+RUN wget "https://huggingface.co/unsloth/Qwen3.5-0.8B-GGUF/resolve/main/mmproj-BF16.gguf" -O /models/mmproj-BF16.gguf
 
 # --- CREATE ROUTER CONFIGURATION ---
 RUN echo "[gemma-4-E2B-it-vision]" > /models.ini && \
@@ -49,8 +50,9 @@ RUN echo "[gemma-4-E2B-it-vision]" > /models.ini && \
     echo "ctx-size = 8192" >> /models.ini && \
     echo "flash-attn = on" && \
     echo "" >> /models.ini && \
-    echo "[qwen-3.5-0.8b]" >> /models.ini && \
-    echo "model = /models/qwen-3.5-0.8b.gguf" >> /models.ini && \
+    echo "[qwen-3.5-0.8b-vision]" >> /models.ini && \
+    echo "model = /models/Qwen3.5-0.8B-Q4_0.gguf" >> /models.ini && \
+    echo "mmproj = /models/mmproj-BF16.gguf" >> /models.ini && \
     echo "ctx-size = 32768" >> /models.ini && \
     echo "flash-attn = on"