Practice insights
Which hyperparameter values are common vs rare — and which correlate with stronger HuggingFace outcomes. Scores are population percentiles in 0–1; the works/fails axis is stratified by base model.
Search the corpus
Semantic search over repo READMEs and model cards — or ask a question and get an answer grounded in the retrieved sources.
Models
HuggingFace LoRA models with outcome signals and the composite success score. Click a row for its extracted training recipe.
| model | base | downloads | likes | fan-out | score |
|---|
Repositories
GitHub repos with extracted LoRA configs. Click a row for the recipe and any linked HuggingFace models.
| repository | language | stars | params | confidence |
|---|