Shortcuts

lora_qwen2_1_5b

torchtune.models.qwen2.lora_qwen2_1_5b(lora_attn_modules: List[Literal['q_proj', 'k_proj', 'v_proj', 'output_proj']], apply_lora_to_mlp: bool = False, lora_rank: int = 8, lora_alpha: float = 16, lora_dropout: float = 0.0, use_dora: bool = False, quantize_base: bool = False) TransformerDecoder[source]

Builder for creating a Qwen2 1.5B model with LoRA enabled.

The Qwen2 defaults are the same as in qwen2_1_5b(), while LoRA default params are based on https://github.com/tloen/alpaca-lora/blob/8bb8579e403dc78e37fe81ffbb253c413007323f/finetune.py#L41-L43.

Parameters:
  • lora_attn_modules (List[LORA_ATTN_MODULES]) – list of which linear layers LoRA should be applied to in each self-attention block. Options are {"q_proj", "k_proj", "v_proj", "output_proj"}.

  • apply_lora_to_mlp (bool) – whether to apply LoRA to the MLP in each transformer layer. Default: False

  • lora_rank (int) – rank of each low-rank approximation

  • lora_alpha (float) – scaling factor for the low-rank approximation

  • lora_dropout (float) – dropout probability for the low-rank approximation. Default: 0.0

  • quantize_base (bool) – Whether to quantize base model weights

Returns:

Instantiation of Qwen2 1.5B model with LoRA applied

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.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources