| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| config | ||
| README.md | ||
| main_ppo_split.py | ||
| run_deepseek7b_llm.sh | ||
| split_monkey_patch.py |
The split placement example is outdated, I tried it and encountered some errors. To address this, the following changes were made in this PR 1. Copied the content from `verl/trainer/config/ppo_trainer.yaml` to `examples/split_placement/config/ppo_trainer_split.yaml` 2. Copied `RayPPOTrainer.fit` method into the `fit` func in `examples/split_placement/split_monkey_patch.py` and modified it to get the futures of `critic_output` and `actor_output`
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| config | Loading commit data... | |
| README.md | Loading commit data... | |
| main_ppo_split.py | Loading commit data... | |
| run_deepseek7b_llm.sh | Loading commit data... | |
| split_monkey_patch.py | Loading commit data... |