llama2_reward_7b¶
- torchtune.models.llama2.llama2_reward_7b() TransformerDecoder[source]¶
Builder for creating a Llama2 model initialized w/ the default 7B parameter values from https://arxiv.org/abs/2307.09288, where the output layer is a classification layer projecting to a single class for reward modelling.
- Returns:
Instantiation of Llama2 7B model
- Return type:
