Open Issues Need Help
View All on GitHub enhancement good first issue
Clean, config-driven LLM Post-Training: SFT, DPO, GRPO, On-Policy Distillation — one YAML, any topology.
Python
utils: add a dataset validator for prompt-only (GRPO / Distill) datasets about 2 months ago
enhancement good first issue
Clean, config-driven LLM Post-Training: SFT, DPO, GRPO, On-Policy Distillation — one YAML, any topology.
Python
ci: add GitHub Actions workflow running ruff and pytest about 2 months ago
enhancement good first issue
Clean, config-driven LLM Post-Training: SFT, DPO, GRPO, On-Policy Distillation — one YAML, any topology.
Python
Fix remaining ruff findings and pin the rule set in pyproject.toml about 2 months ago
enhancement good first issue
Clean, config-driven LLM Post-Training: SFT, DPO, GRPO, On-Policy Distillation — one YAML, any topology.
Python
tests: add unit tests for resample_by_weight (dataset mixture weight:) about 2 months ago
enhancement good first issue
Clean, config-driven LLM Post-Training: SFT, DPO, GRPO, On-Policy Distillation — one YAML, any topology.
Python