`iAddlmZmZddlZddlmZddlmZddlmZddl m Z ddl m Z m Z d d lmZd d lmZmZmZmZmZmZmZmZmZmZd d lmZe jeZGd deZ GddeZ!GddeZ"GddeZ#GddeZ$GddeZ%GddeZ&GddeZ'GddeZ(Gdd eZ)gd!Z*dS)")CallableOptionalN)nn)Cache)ALL_ATTENTION_FUNCTIONS)Unpack)TransformersKwargslogging) LlamaConfig) LlamaAttentionLlamaDecoderLayerLlamaForCausalLMLlamaForTokenClassification LlamaModelLlamaPreTrainedModel LlamaRMSNormLlamaRotaryEmbeddingapply_rotary_pos_embeager_attention_forward) NemotronMLPcneZdZdZdZddddddddZdd d d d d d dddddddddddddddddffd ZxZS) ApertusConfiga This is the configuration class to store the configuration of a [`ApertusModel`]. It is used to instantiate a Apertus model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Apertus-8B. e.g. [swiss-ai/Apertus-8B](https://huggingface.co/swiss-ai/Apertus-8B) Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 131072): Vocabulary size of the Apertus model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ApertusModel`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 14336): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 32): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. hidden_act (`str` or `function`, *optional*, defaults to `"xielu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 65536): The maximum sequence length that this model might ever be used with. Apertus supports up to 65536 tokens. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. pad_token_id (`int`, *optional*, defaults to 3): Padding token id. bos_token_id (`int`, *optional*, defaults to 1): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 2): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings rope_theta (`float`, *optional*, defaults to 12000000.0): The base period of the RoPE embeddings. rope_scaling (`Dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value accordingly. Expected contents: `rope_type` (`str`): The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', 'llama3'], with 'default' being the original RoPE implementation. `factor` (`float`, *optional*): Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In most scaling types, a `factor` of x will enable the model to handle sequences of length x * original maximum pre-trained length. `original_max_position_embeddings` (`int`, *optional*): Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during pretraining. `attention_factor` (`float`, *optional*): Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using the `factor` field to infer the suggested value. `beta_fast` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear ramp function. If unspecified, it defaults to 32. `beta_slow` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear ramp function. If unspecified, it defaults to 1. `short_factor` (`list[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to short contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `long_factor` (`list[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to long contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `low_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE `high_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE attention_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. ```python >>> from transformers import ApertusModel, ApertusConfig >>> # Initializing a Apertus-8B style configuration >>> configuration = ApertusConfig() >>> # Initializing a model from the Apertus-8B style configuration >>> model = ApertusModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```apertus colwise_rep rowwise_repcolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projzlayers.*.mlp.gate_projiii8 Nxieluig{Gz?gh㈵>Trr Fg`fAllama3g @i g?g@) rope_typefactor original_max_position_embeddingslow_freq_factorhigh_freq_factorc tjdid|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d|d|d|||`|`|`dS)N vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads hidden_actmax_position_embeddingsinitializer_range rms_norm_eps use_cache pad_token_id bos_token_id eos_token_idtie_word_embeddings rope_theta rope_scalingattention_biasattention_dropout)super__init__pretraining_tpmlp_biashead_dim)selfr+r,r-r.r/r0r1r2r3r4r5r6r7r8r9r:r;r<r=kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/apertus/modular_apertus.pyr@zApertusConfig.__init__s+:    !z #  0/ 0/  !4 3  !4 3  "z %<$; 0/ &  i & & & !4 3 "z! "&# $*>% &0/)   ,   M MMM)__name__ __module__ __qualname____doc__ model_typebase_model_tp_planr@ __classcell__rFs@rGrr,sh h TJ%2%2%2%2 )"+"+  %!!04" #   55555555555rHrceZdZfdZxZS) ApertusMLPcttj|j|jd|_tj|j|jd|_dS)NF)bias)r?r@rLinearr,r-up_proj down_proj)rDconfigrFs rGr@zApertusMLP.__init__s[ y!143IPUVVV 4#94;KRWXXXrH)rIrJrKr@rOrPs@rGrRrRsAYYYYYYYYYrHrRceZdZdS)ApertusRMSNormNrIrJrKr>rHrGrZrZDrHrZceZdZdS)ApertusRotaryEmbeddingNr[r>rHrGr^r^r\rHr^ceZdZd dedeeffd Z ddejde ejejfdeejdee d eej d e e d e ejejffd ZxZS)ApertusAttentionNrX layer_idxct||t|j|j|_t|j|j|_dSN)r?r@rZrCr4q_normk_normrDrXrarFs rGr@zApertusAttention.__init__sM +++$T]F4GHH $T]F4GHH rH hidden_statesposition_embeddingsattention_maskpast_key_valuescache_positionrEreturnc |jdd}g|d|jR}|||dd} |||dd} |||dd} || } || } |\} } t| | | | \} } |&| | |d}| | | |j |\} } t}|j jdkrt|j j}||| | | |f|jsdn|j|jd|\}}|jg|dR}||}||fS)Nr"r )sincosrkeagerr))dropoutscaling)shaperCq_projview transposek_projv_projrdrerupdaterarrX_attn_implementationrtrainingr=rsreshape contiguouso_proj)rDrgrhrirjrkrE input_shape hidden_shape query_states key_states value_statesrpro cache_kwargsattention_interface attn_output attn_weightss rGforwardzApertusAttention.forwards$)#2#. 88b8$-88 {{=1166|DDNNqRSTT [[//44\BBLLQPQRR {{=1166|DDNNqRSTT {{<00 [[,, &S#7 jRUWZ#[#[ j  &#&snUUL'6'='=j,X\Xfht'u'u $J (? ; +w 6 6"9$+:Z"[ $7$7      % $}HCC$2HL % %  % % ! \*k);;;;;;FFHH kk+.. L((rHrc)NN)rIrJrKrrintr@torchTensortupler LongTensorr r rrOrPs@rGr`r`sII}I#IIIIII,059 *)*)|*)#5<#=>*)!. *) "% *) !!12 *)+,*) u|U\) **)*)*)*)*)*)*)*)rHr`ceZdZdedeffd Z ddejdeejdeej d ee d ee d eej d ee ejejfd e ede ejfdZxZS)ApertusDecoderLayerrXract||t|j|j|_t|j|j|_|`|`dS)N)eps) r?r@rZr,r4attention_layernormfeedforward_layernorminput_layernormpost_attention_layernormrfs rGr@zApertusDecoderLayer.__init__se +++#1&2D&J]#^#^#^ %3F4FFL_%`%`%`"   ) ) )rHNFrgri position_idsrjr5rkrhrErlc |} ||}|jd|||||||d|\}} | |z}|} ||}||}| |z}|S)N)rgrirrjr5rkrhr>)r self_attnrmlp) rDrgrirrjr5rkrhrEresidual_s rGrzApertusDecoderLayer.forward%s!00?? )4>  ')%+) 3       q!=0 !22=AA //  =0 rH)NNNFNN)rIrJrKrrr@rrrrrboolrr r rrOrPs@rGrrs*}*******2637+/$)59KO|!.u/0  "%  D> !!12&eEL%,,F&GH+, u| rHrceZdZdS)ApertusPreTrainedModelNr[r>rHrGrrFr\rHrceZdZdS) ApertusModelNr[r>rHrGrrJr\rHrceZdZfdZxZS)ApertusForCausalLMc 6tjdi|S)an labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing the masked language modeling loss. Indices should either be in `[0, ..., config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`. Example: ```python >>> from transformers import AutoTokenizer, ApertusForCausalLM >>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B") >>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B") >>> prompt = "Hey, are you conscious? Can you talk to me?" >>> inputs = tokenizer(prompt, return_tensors="pt") >>> # Generate >>> generate_ids = model.generate(inputs.input_ids, max_length=30) >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you." ```r>)r?r)rD super_kwargsrFs rGrzApertusForCausalLM.forwardOs!.uww.....rH)rIrJrKrrOrPs@rGrrNs8/////////rHrceZdZdS)ApertusForTokenClassificationNr[r>rHrGrrir\rHr)rrrrr)+typingrrrr cache_utilsrmodeling_utilsrprocessing_utilsr utilsr r llama.configuration_llamar llama.modeling_llamarrrrrrrrrrnemotron.modeling_nemotronr get_loggerrIloggerrrRrZr^r`rrrrr__all__r>rHrGrs  &%%%%%%%  555555&&&&&&00000000333333                        544444  H % %kkkkkKkkk\YYYYYYYY     \        1   0)0)0)0)0)~0)0)0)f'''''+'''T     1        :   /////)///6     $?      rH