Fine-tuning Mistral 7B with QLoRA on Python docstring generation — outperforming Llama 3.3 70B (a model 10x larger) on ROUGE-L and BERTScore at a fraction of the inference cost. Resume bullet: ...
tools/test/docstring_linter_testdata/python_code.py.txt:71: No docstring found for function 'needs_docs' (11 lines). If the method overrides a method on a parent ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results