Shivchander Sudalairaj

Use the open source SDG Hub to quickly create custom synthetic data pipelines. Train and evaluate your models faster and more efficiently.

Discover SDG Hub, an open framework for building, composing, and scaling synthetic data pipelines for large language models.

Learn about an efficient inference scaling method that can improve your model's reasoning ability and performance at runtime while saving on compute costs.

Progress in small LLM reasoning: Our Qwen-32B model, using particle filtering, now surpasses o1-preview on Math500.

On reproducing R1-like reasoning in small LLMs: LIMO dataset ineffective for Llama/Granite; synthetic data generation shows promise but fine-tuning is tricky.

An update on reproducing R1-like reasoning in small LLMs: Granite models show big gains with particle filtering, outperforming GPT-4o on benchmarks.