Language Models

This repository is a collection of experiments with small and large language models, covering fine-tuning, inference, embeddings, and deployment.

Contents

• Fine-tuning workflows for transformers (MiniLM, GPT-2, DistilGPT-2, and similar)
• Agentic workflows with OpenAI
• Model deployment (Flask, FastAPI)

Planned work

• Agentic workflows with small language models
• Instruction-based fine-tuning
• Model deployment (LangServe)