Articles by desideratum
55

Nanocode: The best Claude Code that $200 can buy in pure JAX on TPUs (github.com/salmanmohammadi)

2

Batrachochytrium Dendrobatidis (wikipedia.org)

3

Finetuning GPT-OSS with Axolotl (github.com/axolotl-ai-cloud)

1

Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training (huggingface.co)

3

Training LLMs with GRPO and Interpreter Feedback Using WebAssembly (huggingface.co)

1

Training Large Language Models with Interpreter Feedback Using WebAssembly (huggingface.co)

5

DeepSeek-V3-0324 (huggingface.co)

1

Training Process Reward Models in Axolotl (axolotlai.substack.com)

1

Torchtune – a native PyTorch library for fine-tuning LLMs (github.com/pytorch)

1

(Deep Learning Based) Opportunistic Screening to Improve Statin Rates (ahajournals.org)

1

The theory of Proximal Policy Optimisation implementations (salmanmohammadi.github.io)