Spaces:

jester1177
/

mutant-hunter-env

Sleeping

App Files Files Community

mutant-hunter-env

3.29 MB

Ctrl+K

Ctrl+K

3 contributors

History: 40 commits

Krishna1107's picture

Add Implementation details section and surface YouTube demo URL up top in BLOG

75616fd 20 days ago

docs
Document Phase 1 results and Phase 2 self-play roadmap 20 days ago
evaluation
Reset env between retry attempts within a single episode 20 days ago
final_results
Document Phase 1 results and Phase 2 self-play roadmap 20 days ago
plots
Document Phase 1 results and Phase 2 self-play roadmap 20 days ago
scripts
Drop GRPO temp to 0.3, bump max_new_tokens to 2048, add inference smoke test 20 days ago
src
Re-apply training prep work on top of validated Layers 1-5 base 21 days ago
tests
Initial commit: MutantHunter — RL env for mutation-score-rewarded test generation 21 days ago
training
Drop GRPO temp to 0.3, bump max_new_tokens to 2048, add inference smoke test 20 days ago
.gitignore

1.25 kB
Initial commit: MutantHunter — RL env for mutation-score-rewarded test generation 21 days ago
.python-version

5 Bytes
Initial commit: MutantHunter — RL env for mutation-score-rewarded test generation 21 days ago
BLOG.md

22 kB
Add Implementation details section and surface YouTube demo URL up top in BLOG 20 days ago
Dockerfile

1.46 kB
Prompt fix: include full module source + grounding rule + corpus example; skip baseline recompute when cached 21 days ago
LICENSE

11.3 kB
Initial commit: MutantHunter — RL env for mutation-score-rewarded test generation 21 days ago
PROJECT_BLUEPRINT.md

49.8 kB
Initial commit: MutantHunter — RL env for mutation-score-rewarded test generation 21 days ago
README.md

8.33 kB
Add YouTube demo video link to README and BLOG 20 days ago
openenv.yaml

110 Bytes
Initial commit: MutantHunter — RL env for mutation-score-rewarded test generation 21 days ago
pyproject.toml

2.75 kB
Fix verification gaps: add README links, rename blog, fix Colab badge, set author 20 days ago
requirements.txt

590 Bytes
Initial commit: MutantHunter — RL env for mutation-score-rewarded test generation 21 days ago