model

WizardLM-2-7B-Atlassian

Atlassian-named fine-tune of WizardLM-2-7B posted to Hugging Face in May 2024, publicly surviving only as a GGUF re-quantisation with no documented training data.

Current clusters

build1 publisher

A rank-32 LoRA on one Mac Studio takes Forge manifests from 0 of 25 to 14 of 25

Atlassian's own validator did the grading, on 25 app briefs, on the same workstation that trained the adapter. Anyone reusing the pass rate needs briefs that look like those 25.

Publishers:dev.to

Reality

Evidence55
Adoption15
Hype gap+10
Incentives65
Confidence45