| .. |
|
accelerate_configs
|
704a432249
Add chapter11
|
hai 11 meses |
|
.env.example
|
704a432249
Add chapter11
|
hai 11 meses |
|
00_quick_test.py
|
38507303ec
docs(chapter11): 为 GRPO 学习率补充策略坍塌提示（注释与说明）
|
hai 1 mes |
|
01_dataset_loading.py
|
704a432249
Add chapter11
|
hai 11 meses |
|
02_reward_functions.py
|
704a432249
Add chapter11
|
hai 11 meses |
|
03_lora_configuration.py
|
704a432249
Add chapter11
|
hai 11 meses |
|
04_sft_training.py
|
704a432249
Add chapter11
|
hai 11 meses |
|
05_grpo_training.py
|
38507303ec
docs(chapter11): 为 GRPO 学习率补充策略坍塌提示（注释与说明）
|
hai 1 mes |
|
06_complete_pipeline.py
|
704a432249
Add chapter11
|
hai 11 meses |
|
07_model_evaluation.py
|
704a432249
Add chapter11
|
hai 11 meses |
|
08_distributed_training.py
|
704a432249
Add chapter11
|
hai 11 meses |
|
config.json
|
704a432249
Add chapter11
|
hai 11 meses |
Meredith2328
38507303ec
docs(chapter11): 为 GRPO 学习率补充策略坍塌提示（注释与说明）