harmonic-reasoning-v1

Summary

I'm a PhD student in visual neuroscience at the University of Toronto who also happens to spend way too much time fine-tuning, merging, and quantizing open-weight models on rented H100s and a local DGX Spark. All training compute is self-funded — balancing GPU costs against a student budget. If my open-weight models or datasets have been useful to you, consider supporting future releases.

Keywords

hf-dataset language-modeling · -qa · -reasoning · -math · -code json tabular text datasets pandas polars mlcroissant synthetic reasoning chain-of-thought distillation claude math code science logic thinking sft harmonic

Topics

Language Modeling, QA, Reasoning, Math, Code

Research notes

• downloads=811; likes=26