Small LMs (10M-9B) fine-tuned for financial sentiment with chain-of-thought reasoning. SFT + GRPO across 8 architectures. Base + GGUF builds.
Ayan Shaikh
Ayansk11
AI & ML interests
Large Language Models, LoRA/PEFT Fine-tuning, Reinforcement Learning (GRPO, PPO), Multi-Agent Systems, RAG Pipelines, Financial NLP, Cybersecurity AI, Chain-of-Thought Reasoning
Organizations
None yet