docs: Add Docker build instructions

docker/BUILD_INSTRUCTIONS.md

@@ -0,0 +1,119 @@
+# MiniMind Max2 - Docker Build Instructions
+
+## Quick Start with Docker Buildx Cloud
+
+### 1. Create Cloud Builder
+```bash
+docker buildx create --driver cloud sultanafariabd/minimind
+```
+
+### 2. Build with Cloud Builder
+```bash
+# Clone the model files first
+git clone https://huggingface.co/fariasultana/MiniMind
+cd MiniMind/docker
+
+# Build using cloud builder
+docker buildx build --builder cloud-sultanafariabd-minimind \
+  --platform linux/amd64,linux/arm64 \
+  -t sultanafariabd/minimind-max2:latest \
+  -t sultanafariabd/minimind-max2:v1.0.0 \
+  -t sultanafariabd/minimind-max2:nano \
+  --push .
+```
+
+## Alternative: Standard Docker Build
+
+### 1. Login to Docker Hub
+```bash
+docker login -u sultanafariabd
+# Enter token: dckr_pat_WG_3IV0n-CxJhvAdGB79KHJtJbA
+```
+
+### 2. Build Image
+```bash
+cd MiniMind/docker
+docker build -t sultanafariabd/minimind-max2:latest .
+```
+
+### 3. Push to Docker Hub
+```bash
+docker push sultanafariabd/minimind-max2:latest
+docker tag sultanafariabd/minimind-max2:latest sultanafariabd/minimind-max2:v1.0.0
+docker push sultanafariabd/minimind-max2:v1.0.0
+```
+
+## Run the Container
+
+```bash
+# Run with default settings
+docker run -p 8000:8000 sultanafariabd/minimind-max2:latest
+
+# Run with custom variant
+docker run -p 8000:8000 -e MODEL_VARIANT=max2-lite sultanafariabd/minimind-max2:latest
+
+# Run with GPU support
+docker run --gpus all -p 8000:8000 sultanafariabd/minimind-max2:latest
+```
+
+## API Endpoints
+
+Once running, access the API at `http://localhost:8000`:
+
+| Endpoint | Method | Description |
+|----------|--------|-------------|
+| `/` | GET | Root info |
+| `/health` | GET | Health check |
+| `/info` | GET | Model information |
+| `/docs` | GET | Swagger UI |
+| `/generate` | POST | Generate text with thinking |
+| `/tools/call` | POST | Function calling |
+| `/capabilities` | GET | List capabilities |
+
+## Example API Call
+
+```bash
+curl -X POST http://localhost:8000/generate \
+  -H "Content-Type: application/json" \
+  -d '{
+    "prompt": "Explain quantum computing",
+    "max_tokens": 200,
+    "thinking_mode": "interleaved",
+    "show_thinking": true
+  }'
+```
+
+## Multi-Architecture Build
+
+For ARM64 (Apple Silicon, Raspberry Pi) support:
+
+```bash
+docker buildx build --platform linux/amd64,linux/arm64 \
+  -t sultanafariabd/minimind-max2:latest \
+  --push .
+```
+
+## Docker Compose
+
+```yaml
+version: '3.8'
+services:
+  minimind:
+    image: sultanafariabd/minimind-max2:latest
+    ports:
+      - "8000:8000"
+    environment:
+      - MODEL_VARIANT=max2-nano
+      - PORT=8000
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+```
+
+## Links
+
+- **Docker Hub**: https://hub.docker.com/r/sultanafariabd/minimind-max2
+- **HuggingFace Model**: https://huggingface.co/fariasultana/MiniMind
+- **HuggingFace Space**: https://huggingface.co/spaces/fariasultana/MiniMind-API