qlora_llama3_3_70b

torchtune.models.llama3_3.qlora_llama3_3_70b(lora_attn_modules: List[Literal['q_proj', 'k_proj', 'v_proj', 'output_proj']], apply_lora_to_mlp: bool = False, apply_lora_to_output: bool = False, lora_rank: int = 8, lora_alpha: float = 16, lora_dropout: float = 0.0, use_dora: bool = False, *, quantize_base: bool = True) → TransformerDecoder

Builder for creating a Llama3.3 70B model with QLoRA enabled. Base model weights in linear layers that LoRA is applied to are quantized per the QLoRA paper: https://arxiv.org/abs/2305.14314. Please see lora_llama3_1_70b for full API arguments.