jang1563
/

BioRLHF

Model card Files Files and versions

BioRLHF / scripts

92.8 kB

Ctrl+K

Ctrl+K

2 contributors

History: 3 commits

jang1563's picture

Phase 4: V1-aware calibration verifier, eval tools, cleanup

2145d80 3 months ago

HPC_TRAINING_GUIDE.md

5.62 kB
Phase 4: V1-aware calibration verifier, eval tools, cleanup 3 months ago
analyze_eval.py

27.4 kB
Phase 4: V1-aware calibration verifier, eval tools, cleanup 3 months ago
deploy_to_cayuga.sh

4.11 kB
Add BioGRPO training pipeline with composable biological verifiers 3 months ago
evaluate_ecosystem_model.py

13.4 kB
Add BioGRPO training pipeline with composable biological verifiers 3 months ago
evaluate_grpo.py

13.5 kB
Phase 4: V1-aware calibration verifier, eval tools, cleanup 3 months ago
merge_training_data.py

4.95 kB
Add BioGRPO training pipeline with composable biological verifiers 3 months ago
run_eval_grpo.sh

3.91 kB
Phase 4: V1-aware calibration verifier, eval tools, cleanup 3 months ago
run_evaluation.sh

2.33 kB
Add BioGRPO training pipeline with composable biological verifiers 3 months ago
run_grpo_full.sh

2.61 kB
Phase 3: Fix GRPO learning signal with continuous rewards and multi-reward 3 months ago
run_grpo_mve.sh

2.69 kB
Add BioGRPO training pipeline with composable biological verifiers 3 months ago
run_grpo_phase4.sh

2.64 kB
Phase 4: V1-aware calibration verifier, eval tools, cleanup 3 months ago
setup_cayuga_grpo.sh

4.36 kB
Add BioGRPO training pipeline with composable biological verifiers 3 months ago
train_ecosystem_improved.sh

5.37 kB
Add BioGRPO training pipeline with composable biological verifiers 3 months ago