MyPO Project
MyPO models, datasets, training assets, and live dashboard for typed Python preference tuning.
Viewer • Updated • 6.36k • 121 • 2Note Core MyPO DPO dataset: chosen vs rejected Python code quality pairs.
joshuasundance/mypo-4k-rfc-val-phi3test
Viewer • Updated • 100 • 12Note Legacy validation comparison subset for the Phi-3 MyPO line.
joshuasundance/phi3-mini-4k-qlora-python-code-20k-mypo-4k-rfc
Updated • 1Note Legacy Phi-3 MyPO adapter experiment.
joshuasundance/phi3-mini-4k-qlora-python-code-20k-mypo-4k-rfc-full
Text Generation • 4B • Updated • 3Note Legacy Phi-3 full/merged MyPO model.
joshuasundance/phi3-mini-4k-qlora-python-code-20k-mypo-4k-rfc-pipe
Text Generation • 4B • Updated • 18 • 1Note Legacy Phi-3 pipeline-export MyPO model used in early comparisons.
joshuasundance/mypo-training
UpdatedNote Training scripts, reports, evaluation artifacts, and durable HumanEval+ pipeline source of truth.
joshuasundance/mypo-qwen2.5-coder-1.5b-sft
Text Generation • Updated • 149Note Qwen 2.5 Coder SFT LoRA adapter for typed Python generation.
joshuasundance/mypo-qwen2.5-coder-1.5b-dpo-v2
Text Generation • Updated • 163Note Qwen 2.5 Coder DPO v2 LoRA adapter; reproducibility artifact and near-base baseline.
joshuasundance/mypo-qwen2.5-coder-1.5b-dpo-v3
Text Generation • 2B • Updated • 1.07kNote Qwen 2.5 Coder DPO v3 merged model; strongest in-domain type-hint preference model in the project.
mypo HumanEval+ live
📊Monitor HumanEval+ runs with a live dashboard
Note Live dashboard for the durable HumanEval+ pipeline and canonical benchmark runs.