feat: add distilbert sentiment classification model

[TimPietruskyRunPod]

Summary

Add DistilBERT sentiment classification model to the Runpod template with comprehensive documentation.

Changes

• Bake DistilBERT sentiment model into Docker image
• Add transformers library dependency (4.40.0+)
• Implement sentiment analysis pipeline with local_files_only=True
• Document both model download methods: transformers pipeline and wget
• Add example inference code for sentiment classification
• Model loads from cache without network access at runtime
• Support CUDA GPU acceleration or CPU fallback
• Include wget alternative for custom/hosted models
• Clarify use cases and options in code comments

Use Cases Documented

1. Model Baking: Two options for baking models into the image

   • Option 1: Automatic via transformers pipeline (default)
   • Option 2: Manual via wget (alternative)

2. Service Startup: Three options for container startup

   • Option 1: Jupyter + SSH (default)
   • Option 2: Services + custom app
   • Option 3: App only (production)

Testing

• Model loads successfully from cache
• Inference works correctly on both GPU and CPU
• Both model baking methods tested and working