update flashattn, fix ppo save model

Former-commit-id: 0b08bc3dac246d4aa3f89afb7172529dcad9c39f
2023-09-11 17:25:36 +08:00
parent a09a7b650d
commit 42e0b30476
5 changed files with 105 additions and 518 deletions
--- a/src/llmtuner/tuner/dpo/trainer.py
+++ b/src/llmtuner/tuner/dpo/trainer.py
@@ -26,6 +26,7 @@ class CustomDPOTrainer(DPOTrainer):
            if ref_model is not None:
                disable_dropout_in_model(ref_model)

+        self.is_encoder_decoder = model.config.is_encoder_decoder
        self.ref_model = ref_model
        self.use_dpo_data_collator = True # hack to avoid warning
        self.label_pad_token_id = IGNORE_INDEX