bCiASSKJrJr SSKrSSKJr SSKJr SSKJr SSK J r SSK J r J r S S KJr S S KJrJrJrJrJrJrJrJrJrJr S S KJr \ R:"\5r"S S\5r "SS\5r!"SS\5r""SS\5r#"SS\5r$"SS\5r%"SS\5r&"SS\5r'"SS\5r("SS \5r)/S!Qr*g)")CallableOptionalN)nn)Cache)ALL_ATTENTION_FUNCTIONS)Unpack)TransformersKwargslogging) LlamaConfig) LlamaAttentionLlamaDecoderLayerLlamaForCausalLMLlamaForTokenClassification LlamaModelLlamaPreTrainedModel LlamaRMSNormLlamaRotaryEmbeddingapply_rotary_pos_embeager_attention_forward) NemotronMLPcz^\rSrSrSrSrSSSSSSSS.rS S S S S S SSSSSSSSSSSSSSSS.SS4U4SjjrS rU=r $)! ApertusConfig,aZ 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 >[TU]"S0SU_SU_SU_SU_SU_SU_SU_SU_S U _S U _S U _S U _S U _SU_SU_SU_SU_SU_SU_UD6 U?U?U?g)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/r0r1r2r3r4r5r6r7r8r9r:r;r<r=r>kwargs __class__s e/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/apertus/modular_apertus.pyrAApertusConfig.__init__s:  ! # 0 0  !4  !4  " %< 0 &   & & & !4 "! "&# $*% &0) ,   M Mr?) __name__ __module__ __qualname____firstlineno____doc__ model_typebase_model_tp_planrA__static_attributes__ __classcell__rGs@rHrr,sh TJ%2%2%2%2 )"+"+  %!!04" #  555rJrc(^\rSrSrU4SjrSrU=r$) ApertusMLPc>[TU]5 [R"URUR SS9Ul[R"UR URSS9Ulg)NF)bias)r@rArLinearr-r.up_proj down_proj)rEconfigrGs rHrAApertusMLP.__init__sP yy!1!143I3IPUV 4#9#94;K;KRWXrJ)r\r[)rKrLrMrNrArRrSrTs@rHrVrVsYYrJrVc\rSrSrSrg)ApertusRMSNormr?NrKrLrMrNrRr?rJrHr`r`rJr`c\rSrSrSrg)ApertusRotaryEmbeddingr?Nrbr?rJrHrerercrJrec$^\rSrSrSS\S\\4U4SjjjrSS\RS\ \R\R4S\\RS\\ S \\RS \ \S \ \R\R44S jjrS rU=r$)ApertusAttentionr] layer_idxc>[TU]X5 [URUR5Ul[URUR5UlgN)r@rAr`rDr5q_normk_normrEr]rjrGs rHrAApertusAttention.__init__s@ +$T]]F4G4GH $T]]F4G4GH rJ hidden_statesposition_embeddingsattention_maskpast_key_valuescache_positionrFreturnc xURSSn/UQSPURP7nURU5RU5R SS5n UR U5RU5R SS5n UR U5RU5R SS5n URU 5n URU 5n Uup[XX5upUb$XUS.nURXURU5up[nURRS:wa[URRnU"UU U U U4UR (dSO UR"UR$S.UD6unnUR&"/UQSP76R)5nUR+U5nUU4$)Nr#r )sincosrueagerr*)dropoutscaling)shaperDq_projview transposek_projv_projrmrnrupdaterjrr]_attn_implementationrtrainingr>r}reshape contiguouso_proj)rErqrrrsrtrurF input_shape hidden_shape query_states key_states value_statesrzry cache_kwargsattention_interface attn_output attn_weightss rHforwardApertusAttention.forwards$))#2. 88b8$--8 {{=166|DNNqRST [[/44\BLLQPQR {{=166|DNNqRST {{<0 [[, &#7 RU#[  &#&nUL'6'='=jX\XfXfht'u $J(? ;; + +w 6"9$++:Z:Z"[ $7      % $}}C$2H2HLL %  % ! \"));;;;FFH kk+. L((rJ)rnrmrl)NN)rKrLrMrNrrintrAtorchTensortupler LongTensorr r rrRrSrTs@rHrhrhsI}I#II,059 *)||*)#5<<#=>*)!. *) "% *) !!1!12 *)+,*) u||U\\) **)*)rJrhc8^\rSrSrS\S\4U4SjjrSS\RS\ \RS\ \RS\ \ S \ \ S \ \RS \ \ \R\R4S \\S \ \R4SjjrSrU=r$)ApertusDecoderLayerir]rjc>[TU]X5 [URURS9Ul[URURS9UlU?U?g)N)eps) r@rAr`r-r5attention_layernormfeedforward_layernorminput_layernormpost_attention_layernormros rHrAApertusDecoderLayer.__init__sR +#1&2D2D&J]J]#^ %3F4F4FFL_L_%`"   )rJrqrs position_idsrtr6rurrrFrvc Un URU5nUR"SUUUUUUUS.UD6upX-nUn URU5nURU5nX-nU$)N)rqrsrrtr6rurrr?)r self_attnrmlp) rErqrsrrtr6rurrrFresidual_s rHrApertusDecoderLayer.forward%s!00? >>  ')%+) 3     !0 !22=A /  0 rJ)rr)NNNFNN)rKrLrMrNrrrArrrrrboolrr r rrRrSrTs@rHrrs*}**2637+/$)59KO||!.u//0  "%  D> !!1!12&eELL%,,,F&GH+, u|| rJrc\rSrSrSrg)ApertusPreTrainedModeliFr?Nrbr?rJrHrrFrcrJrc\rSrSrSrg) ApertusModeliJr?Nrbr?rJrHrrJrcrJrc(^\rSrSrU4SjrSrU=r$)ApertusForCausalLMiNc $>[TU]"S0UD6$)a 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)rE super_kwargsrGs rHrApertusForCausalLM.forwardOs.w...rJr?)rKrLrMrNrrRrSrTs@rHrrNs //rJrc\rSrSrSrg)ApertusForTokenClassificationiir?Nrbr?rJrHrrircrJr)rrrrr)+typingrrrr cache_utilsrmodeling_utilsrprocessing_utilsr utilsr r llama.configuration_llamar llama.modeling_llamarrrrrrrrrrnemotron.modeling_nemotronr get_loggerrKloggerrrVr`rerhrrrrr__all__r?rJrHrs &  5&03   5   H %kKk\YY \  1 0)~0)f'+'T 1  : /)/6 $?  rJ