PiS7ddlmZmZddlmZddlmZmZmZm Z ddl m Z ddl m Z ddlmZddlmZddlmZ d e fd Zd*d edeedeed e fdZ d+deedededededededed e fdZeedZd e_d e fd!Z d+deedededededededed e fd"ZeedZd#e_d e fd$Z d+deedededededededed e fd%Z ee dZ!d&e!_d e fd'Z" d+deedededededededed e fd(Z#eedZ$d)e$_d S),)ListOptional)partial)llama2 lora_llama2llama2_classifierlora_llama2_classifier)TransformerDecoder)Llama2Tokenizer)LORA_ATTN_MODULES) _TemplateType)_get_prompt_templatereturnc 0tddddddddS)z Builder for creating a Llama2 model initialized w/ the default 7B parameter values from https://arxiv.org/abs/2307.09288 Returns: TransformerDecoder: Instantiation of Llama2 7B model } h㈵>) vocab_size num_layers num_heads num_kv_heads embed_dim max_seq_len attn_dropoutnorm_epsr{/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/torchtune/models/llama2/_model_builders.py llama2_7br"s3     r N*torchtune.models.llama2.Llama2ChatTemplatepathrprompt_templatecHt|||t|ndS)a Tokenizer for Llama2. Args: path (str): path to the tokenizer max_seq_len (Optional[int]): maximum sequence length for tokenizing a single list of messages, after which the input will be truncated. Default is None. prompt_template (Optional[_TemplateType]): optional specified prompt template. If a string, it is assumed to be the dotpath of a :class:`~torchtune.data.PromptTemplateInterface` class. If a dictionary, it is assumed to be a custom prompt template mapping role to the prepend/append tags. Default is :class:`~torchtune.models.llama2.Llama2ChatTemplate`. Returns: Llama2Tokenizer: Instantiation of the Llama2 tokenizer Nr$rr%)r rr's r!llama2_tokenizerr(-sG +yHyTOcdsOtOtOtZ^ _ _ __r Frlora_attn_modulesapply_lora_to_mlpapply_lora_to_output lora_rank lora_alpha lora_dropoutuse_dora quantize_basecvtdid|d|d|ddddddd dd d d d d dddd|d|d|d|d|S)aJ Builder for creating a Llama2 7B model with LoRA enabled. The Llama2 defaults are the same as in :func:`~torchtune.models.llama2.llama2_7b`, while LoRA default params are based on https://github.com/tloen/alpaca-lora/blob/8bb8579e403dc78e37fe81ffbb253c413007323f/finetune.py#L41-L43. Args: 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 apply_lora_to_output (bool): whether to apply LoRA to the model's final output projection. Default: False lora_rank (int): rank of each low-rank approximation lora_alpha (float): scaling factor for the low-rank approximation lora_dropout (float): LoRA dropout probability. Default: 0.0 use_dora (bool): Decompose the LoRA weight into magnitude and direction, as introduced in "DoRA: Weight-Decomposed Low-Rank Adaptation" (https://arxiv.org/abs/2402.09353). quantize_base (bool): Whether to quantize base model weights Returns: TransformerDecoder: Instantiation of Llama2 7B model with LoRA applied r+r,r-rrrrrrrrrrrrrr.r/r0r1r2rrr+r,r-r.r/r0r1r2s r!lora_llama2_7br6@sF    ++ ++ 21 6   2   "  R $ D S  ) : "\   $m! r T)r2z Builder for creating a Llama2 7B 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_llama2_7b` for full API arguments. c 2tddddddddd S) z Builder for creating a Llama2 model initialized w/ the default 13B parameter values from https://arxiv.org/abs/2307.09288 Returns: TransformerDecoder: Instantiation of Llama2 13B model r(6rrr rrrrrintermediate_dimrrrrrr r! llama2_13br=s6     r c|tdid|d|d|ddddddd dd d d d ddddddd|d|d|d|d|S)a Builder for creating a Llama2 13B model with LoRA enabled. The Llama2 defaults are the same as in :func:`~torchtune.models.llama2.llama2_13b`, while LoRA default params are based on https://github.com/tloen/alpaca-lora/blob/8bb8579e403dc78e37fe81ffbb253c413007323f/finetune.py#L41-L43. Args: 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 apply_lora_to_output (bool): whether to apply LoRA to the model's final output projection. Default: False lora_rank (int): rank of each low-rank approximation lora_alpha (float): scaling factor for the low-rank approximation use_dora (bool): Decompose the LoRA weight into magnitude and direction, as introduced in "DoRA: Weight-Decomposed Low-Rank Adaptation" (https://arxiv.org/abs/2402.09353). quantize_base (bool): Whether to quantize base model weights Returns: TransformerDecoder: Instantiation of Llama2 13B model with LoRA applied r+r,r-rrrr8rrrr9r<r:rrrrrrr.r/r0r1r2rr4r5s r!lora_llama2_13br?sF    ++ ++ 21 6   2   "  R $  D S  ) : "\  ! "$m# r z Builder for creating a Llama2 13B 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_llama2_13b` for full API arguments. c 2tddddddddd S) z Builder for creating a Llama2 model initialized w/ the default 70B parameter values from https://arxiv.org/abs/2307.09288 Returns: TransformerDecoder: Instantiation of Llama2 70B model rP@r) prrrr;rrr r! llama2_70brEs6     r c|tdid|d|d|dddddd d d d d ddddddddd|d|d|d|d|S)aE Builder for creating a Llama2 70B model with LoRA enabled. The Llama2 defaults are the same as in :func:`~torchtune.models.llama2.llama2_70b`, while LoRA default params are based on https://github.com/tloen/alpaca-lora/blob/8bb8579e403dc78e37fe81ffbb253c413007323f/finetune.py#L41-L43. Args: 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 apply_lora_to_output (bool): whether to apply LoRA to the model's final output projection. Default: False lora_rank (int): rank of each low-rank approximation lora_alpha (float): scaling factor for the low-rank approximation lora_dropout (float): LoRA dropout probability. Default: 0.0 use_dora (bool): Decompose the LoRA weight into magnitude and direction, as introduced in "DoRA: Weight-Decomposed Low-Rank Adaptation" (https://arxiv.org/abs/2402.09353). quantize_base (bool): Whether to quantize base model weights Returns: TransformerDecoder: Instantiation of Llama2 70B model with LoRA applied r+r,r-rrrrArrBrr)rrCrrr<rDrrrrr.r/r0r1r2rr4r5s r!lora_llama2_70brGsF    ++ ++ 21 6   2   "  Q $ D  S  ) : "\  ! "$m# r z Builder for creating a Llama2 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_llama2_70b` for full API arguments. c 2tddddddddd S)a: 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: TransformerDecoder: Instantiation of Llama2 7B model rrrrr) num_classesrrrrrrrr)rrr r!llama2_reward_7brK*s6     r c|tdid|d|d|dddddd d d d d d d dd ddddd|d|d|d|d|S)a Builder for creating a Llama2 7B reward model with LoRA enabled. The Llama2 classifier defaults are the same as in :func:`~torchtune.models.llama2.llama2_reward_7b`, while LoRA default params are based on https://github.com/tloen/alpaca-lora/blob/8bb8579e403dc78e37fe81ffbb253c413007323f/finetune.py#L41-L43. Args: 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 apply_lora_to_output (bool): whether to apply LoRA to the model's final output projection. Default: False lora_rank (int): rank of each low-rank approximation lora_alpha (float): scaling factor for the low-rank approximation lora_dropout (float): LoRA dropout probability. Default: 0.0 quantize_base (bool): Whether to quantize base model weights Returns: TransformerDecoder: Instantiation of Llama2 7B model with LoRA applied r+r,r-rJrIrrrrrrrrrrrrrr.r/r0r1r2r)r r5s r!lora_llama2_reward_7brM@sB "   ++ ++ 21 A   6   2  " R $ D S  ) : "\  ! "$m# r z Builder for creating a Llama2 reward 7b 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_llama2_reward_7b` for full API arguments. )Nr#)FFr)r*rFF)%typingrr functoolsr+torchtune.models.llama2._component_buildersrrrr torchtune.modulesr "torchtune.models.llama2._tokenizerr torchtune.modules.peftr torchtune.data._prompt_templatesr rr"strintr(boolfloatr6qlora_llama2_7b__doc__r=r?qlora_llama2_13brErGqlora_llama2_70brKrMqlora_llama2_reward_7brr r!r^s2 "!!!!!!!vvvvvvvvvvvv000000>>>>>>444444::::::AAAAAA%(__3_Xc]_T\]jTk_`o____*$!&44-.444 4  4  4444444n'.===&.$!&55-.555 5  5  5555555p7?$???&.$!&55-.555 5  5  5555555p7?$???,0$!&33-.333 3  3  3333333l!tDDD"r