| .. |
|
__init__.py
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
conversational_style_dpo_env.py
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsm8k_dpo_rollouts_1.html
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsm8k_dpo_rollouts_2.html
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsm8k_dpo_rollouts_4.html
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsm8k_dpo_rollouts_6.html
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsm8k_dpo_rollouts_8.html
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsm8k_dpo_rollouts_9.html
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsm8k_dpo_rollouts_15.html
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
gsmk8k_conversational_style_dpo_env.py
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
requirements.txt
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |
|
train_dpo_conversational.py
|
dev - push for submission
|
2025-05-18 17:50:15 -07:00 |