PiddlmZmZddlmZmZmZmZddlm Z ddlm Z ddl m Z ddl mZddlmZddlmZ d e fd Zd$d edeedee d efdZ d%deedededededededed e fdZeedZd e_d e fd!Z d%deedededededededed e fd"ZeedZd#e_d S)&)ListOptional)mistral lora_mistralmistral_classifierlora_mistral_classifier) _TemplateType)_get_prompt_template)TransformerDecoder)MistralTokenizer)LORA_ATTN_MODULES)partialreturnc 2tddddddddd S) z Builder for creating a Mistral 7B model initialized w/ the default 7b parameter values from https://mistral.ai/news/announcing-mistral-7b/ Returns: TransformerDecoder: Instantiation of Mistral 7B model } 8h㈵>) vocab_size num_layers num_heads num_kv_heads embed_dimintermediate_dim max_seq_len attn_dropoutnorm_eps)r|/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/torchtune/models/mistral/_model_builders.py mistral_7br%s6     r#N,torchtune.models.mistral.MistralChatTemplatepathrprompt_templatecHt|||t|ndS)a Tokenizer for Mistral models. Args: path (str): path to the tokenizer max_seq_len (Optional[int]): maximum sequence length for tokenizing a single list of messages, after which the input will be truncated. Default is None. prompt_template (Optional[_TemplateType]): optional specified prompt template. If a string, it is assumed to be the dotpath of a :class:`~torchtune.data.PromptTemplateInterface` class. If a dictionary, it is assumed to be a custom prompt template mapping role to the prepend/append tags. Default is :class:`~torchtune.models.mistral.MistralChatTemplate`. Returns: MistralTokenizer: Instantiation of the Mistral tokenizer Nr'rr()r r r*s r$mistral_tokenizerr+3sG ;zIzUPdetPuPuPu[_ ` ` ``r#Frrlora_attn_modulesapply_lora_to_mlpapply_lora_to_output lora_rank lora_alpha lora_dropoutuse_dora quantize_basectdid|d|d|ddddddd d d d d dddddddddd|d|d|d|d|S)ao Builder for creating a Mistral 7B model with LoRA enabled. 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): dropout probability for the low-rank approximation. 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 Mistral 7B model with LoRA applied r-r.r/rrrrrrrrrrrrrr rr!r rope_base'r0r1r2r3r4r")rr-r.r/r0r1r2r3r4s r$lora_mistral_7br9Fs>    ++ ++ 21 6   2   "  Q $  E S  & ) :  "\! "# $$m% r#T)r4z Builder for creating a Mistral 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_mistral_7b` for full API arguments. c 4tdddddddddd S) a~ Builder for creating a Mistral 7B model initialized w/ the default 7b parameter values from: https://huggingface.co/Ray2333/reward-model-Mistral-7B-instruct-Unified-Feedback where the output layer is a classification layer projecting to a single class for reward modelling. Returns: TransformerDecoder: Instantiation of Mistral 7B classifier model rrrrrrrr) num_classesrrrrrrrr r!)rr"r#r$mistral_reward_7br=s9     r#ctdid|d|d|dddddd d d d d d dddddddddddd|d|d|d|d|S)av Builder for creating a Mistral reward 7B model with LoRA enabled. Args: lora_attn_modules (List[LORA_ATTN_MODULES]): list of which linear layers LoRA should be applied to in each self-attention block. Options are ``{"q_proj", "k_proj", "v_proj", "output_proj"}``. apply_lora_to_mlp (bool): whether to apply LoRA to the MLP in each transformer layer. Default: False apply_lora_to_output (bool): whether to apply LoRA to the model's final output projection. Default: False lora_rank (int): rank of each low-rank approximation lora_alpha (float): scaling factor for the low-rank approximation lora_dropout (float): dropout probability for the low-rank approximation. Default: 0.0 use_dora (bool): Decompose the LoRA weight into magnitude and direction, as introduced in "DoRA: Weight-Decomposed Low-Rank Adaptation" (https://arxiv.org/abs/2402.09353). quantize_base (bool): Whether to quantize base model weights Returns: TransformerDecoder: Instantiation of Mistral 7B model with LoRA applied r-r.r/r<r;rrrrrrrrrrrrrr rr!rr6r7r0r1r2r3r4r")rr8s r$lora_mistral_reward_7br?s> #   ++ ++ 21 A   6   2  " Q $  E S  & )  :! ""\# $% &$m' r#a Builder for creating a Mistral 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_mistral_reward_7b` for full API arguments. )Nr&)FFrr,rFF)typingrr,torchtune.models.mistral._component_buildersrrrr torchtune.data._prompt_templatesr r torchtune.modulesr #torchtune.models.mistral._tokenizerr torchtune.modules.peftr functoolsrr%strintr+boolfloatr9qlora_mistral_7b__doc__r=r?qlora_mistral_reward_7br"r#r$rNs "!!!!!!! ;:::::AAAAAA000000@@@@@@444444 &,``C`hsm`U]^kUl`cs````*$!&22-.222 2  2  2222222j7?$???-4$!&33-.333 3  3  3333333l"'"8MMM#r#