rlpost Mattral · PARTIAL
LLM post-training from scratch: SFT, reward model, PPO, DPO; parity-tested against TRL
github.com/Mattral/rlpost · ★ 28 · Forks 6 · Size 676 KB
SUMMARY
Technologies 15
Scored 2
Observed 2
Practices 16
Evidence 25
Skips 13
COVERAGE
Analyzed 60 files · 29 commits · 77 API calls
TECHNOLOGIES & DEPTH
AWS SDK CLOUD Depth —
0 files · config only
Black QUALITY Depth —
0 files · config only
Blinker LIBRARY Depth —
0 files · config only
Click LIBRARY Depth —
0 files · config only
Jinja2 LIBRARY Depth —
0 files · config only
MarkupSafe LIBRARY Depth —
0 files · config only
NumPy LIBRARY Depth —
0 files · config only
Pydantic LIBRARY Depth 58
1 files · PRODUCTION
Requests LIBRARY Depth —
0 files · config only
Werkzeug LIBRARY Depth —
0 files · config only
lxml LIBRARY Depth —
0 files · config only
mypy QUALITY Depth —
0 files · config only
pandas LIBRARY Depth —
0 files · config only
pytest TESTING Depth 45
3 files · TEST
typing_extensions LIBRARY Depth —
0 files · config only
PRACTICES
automated_tests · observedci_dependency_cache · absentci_format_check · observedci_lint · observedci_release_automation · absentci_runs_tests · observedci_security_scan · observedci_type_check · observedcontinuous_integration · observeddocumentation · observeddocumentation_source_ratio · observedformatting · observedmodule_test_ratio · observedsecurity_scanning · observedtest_source_ratio · observedtype_checking · observed
ACTIVITY & OWNERSHIP
First commit 2024-02-03
Last commit 2026-06-06
Active months 4
Commits 29