qwen2_0_5b

torchtune.models.qwen2.qwen2_0_5b() → TransformerDecoder

Builder for creating a Qwen2 model initialized w/ the default 0.5B parameter values from https://huggingface.co/Qwen/Qwen2-0.5B-Instruct

Returns:

Instantiation of Qwen2 0.5B model

Return type:

TransformerDecoder

Note

Qwen2 0.5B and Qwen2 1.5B model builders will enable tie_word_embeddings by default and returns an instance of TransformerDecoder.