Small Language Models (SLMs)
Deploy efficient Small Language Models for production.
Course Duration: 8 hours
What You'll Learn
- SLMs vs LLMs trade-offs
- Model selection criteria
- Quantization techniques
- Edge deployment
- Fine-tuning SLMs
- Cost optimization
Prerequisites
- LLM fundamentals
- Python programming
Course Modules
- Introduction to SLMs
- Phi-3 (Microsoft)
- Gemma (Google)
- Mistral 7B / Mixtral
- Qwen (Alibaba)
- LLaMA 3 8B
- Quantization (GGUF, AWQ, GPTQ)
- Memory Optimization
- Edge Deployment
- Fine-tuning SLMs
- Benchmarking
- Project: Deploy SLM on Raspberry Pi
Models Covered
- Phi-3 Mini/Small/Medium
- Gemma 2B/7B
- Mistral 7B
- Qwen 2.5
- LLaMA 3 8B