Upload 3 files

update corresponding app.py

Dockerfile

@@ -5,8 +5,6 @@ RUN apt-get update && \
     apt-get install -y \
     build-essential \
     python3-dev \
-    git \
-    wget \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
@@ -17,9 +15,7 @@ RUN pip install --no-cache-dir -r requirements.txt
 
 # Create model directory
 RUN mkdir -p /app/models
-
-# Download the GGUF model (replace with your preferred Qwen GGUF model)
-RUN wget -P /app/models https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf
+COPY DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf /app/models/
 
 # Copy application code
 COPY . .

app.py

@@ -16,7 +16,7 @@ logging.basicConfig(
 logger = logging.getLogger(__name__)
 
 # Initialize LLM
-MODEL_PATH = "/app/models/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf"
+MODEL_PATH = "/app/models/DeepSeek-R1-Distill-Qwen-1.5B-Q3_K_M.gguf"
 
 try:
     llm = Llama(