qwen2_5_3b

torchtune.models.qwen2_5.qwen2_5_3b() → TransformerDecoder

Builder for creating a Qwen2.5 model (base or instruct) initialized w/ the default 3B parameter values from https://huggingface.co/Qwen/Qwen2.5-3B-Instruct

Returns:

Instantiation of Qwen2.5 3B model

Return type:

TransformerDecoder

Note

Qwen2.5 0.5B-3B model builders will enable tie_word_embeddings by default (see qwen2())