Stories by desideratum

Finetuning GPT-OSS with Axolotl

Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training

Training LLMs with GRPO and Interpreter Feedback Using WebAssembly

Training Large Language Models with Interpreter Feedback Using WebAssembly

DeepSeek-V3-0324

Training Process Reward Models in Axolotl

Torchtune – a native PyTorch library for fine-tuning LLMs

(Deep Learning Based) Opportunistic Screening to Improve Statin Rates

The theory of Proximal Policy Optimisation implementations

Ask HN: Feel like I'm being lowballed by founders. Where do I go from here?