diff --git a/rewardbench/models/__init__.py b/rewardbench/models/__init__.py index 7ebba8d..532e884 100644 --- a/rewardbench/models/__init__.py +++ b/rewardbench/models/__init__.py @@ -222,7 +222,6 @@ "custom_dialogue": False, "model_type": "Seq. Classifier", }, - } DPO_MODEL_CONFIG = { diff --git a/rewardbench/models/qrm.py b/rewardbench/models/qrm.py index a1df753..dd7fa41 100644 --- a/rewardbench/models/qrm.py +++ b/rewardbench/models/qrm.py @@ -5,10 +5,7 @@ import torch.nn as nn import torch.nn.functional as F import torch.utils.checkpoint -from transformers import ( - LlamaModel, - LlamaPreTrainedModel, -) +from transformers import LlamaModel, LlamaPreTrainedModel from transformers.models.llama.modeling_llama import LLAMA_INPUTS_DOCSTRING from transformers.utils import ModelOutput, add_start_docstrings_to_model_forward