hLddlmZmZddlZddlmZddlmZddlm Z m Z ddl m Z ddl mZmZddlmZdd lmZmZdd lmZdd lmZd d lmZd dlmZmZmZmZm Z m!Z!m"Z"m#Z#m$Z$GddeZ%Gdde!Z&GddeZ'GddeZ(Gdde"Z)Gdde Z*GddeZ+GddeZ,gdZ-y) )CallableOptionalN)TransformersKwargs)Cache DynamicCache)layer_type_validation)create_causal_mask!create_sliding_window_causal_mask)BaseModelOutputWithPast)ROPE_INIT_FUNCTIONSrope_config_validation)ALL_ATTENTION_FUNCTIONS)Unpack) Olmo2Config) Olmo2AttentionOlmo2DecoderLayerOlmo2ForCausalLM Olmo2ModelOlmo2PreTrainedModel Olmo2RMSNormOlmo2RotaryEmbeddingapply_rotary_pos_embeager_attention_forwardceZdZdZdZddddddddZdgd gfd d gd gfd gd gfd Z dfd ZdZxZ S) Olmo3Configa This is the configuration class to store the configuration of a [`Olmo3Model`]. It is used to instantiate an OLMo3 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 [allenai/OLMo-3-0725-1B](https://huggingface.co/allenai/OLMo-3-0725-1B). 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 50304): Vocabulary size of the Olmo3 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Olmo3Model`] hidden_size (`int`, *optional*, defaults to 4096): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 11008): 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 `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 2048): The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. 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 1): Padding token id. bos_token_id (`int`, *optional*): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 50279): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings rope_theta (`float`, *optional*, defaults to 10000.0): 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`, defaults to `False`, *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. rms_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the rms normalization layers. sliding_window (`int`, *optional*, defaults to 4096): Size of the sliding window for sliding window attention. layer_types (`list`, *optional*): Attention pattern for each layer. Defaults to sliding window attention for 3 out of 4 layers, and full attention for every 4th layer. ```python >>> from transformers import Olmo3Model, Olmo3Config >>> # Initializing a Olmo3 7B style configuration >>> configuration = Olmo3Config() >>> # Initializing a model from the Olmo3 7B style configuration >>> model = Olmo3Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` olmo3 colwise_rep rowwise_repcolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.gate_projzlayers.*.mlp.up_projzlayers.*.mlp.down_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnormc ht|did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d|d|d||||_||_|j5t |j Dcgc]}|dzdzdk7rdndc}|_t |jycc}w)N vocab_size hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headsnum_key_value_heads hidden_actmax_position_embeddingsinitializer_range use_cache pad_token_id bos_token_id eos_token_idtie_word_embeddings rope_theta rope_scalingattention_biasattention_dropout rms_norm_epsrsliding_attentionfull_attention)super__init__sliding_window layer_typesranger.r )selfr+r,r-r.r/r0r1r2r3r4r5r6r7r8r9r:r;r<r=rErFkwargsi __class__s f/var/www/html/aiagenthome/venv/lib/python3.12/site-packages/transformers/models/olmo3/modular_olmo3.pyrDzOlmo3Config.__init__sB2  ! # 0 0  !4  !4  " %< 0   & & & !4 " &! "*# $0% &&) .-&    #W\]a]s]sWt WtRSA{a'7#=MMWt D  d../ s;B/ct|y)z< Validate the `rope_scaling` configuration. N)r)rHs rL_rope_scaling_validationz$Olmo3Config._rope_scaling_validations  t$)ii+ rQNsiluig{Gz?Tr>NigFg@NFgh㈵>rPN) __name__ __module__ __qualname____doc__ model_typebase_model_tp_planbase_model_pp_planrDrN __classcell__rKs@rLrr,sm^J%2%2%2%2"+ )"+&(9:#%568IJ!"_$56  $!-60p%rOrc eZdZy) Olmo3RMSNormNrTrUrVrBrOrLr^r^rOr^ceZdZdedeffd Z d dejdeejejfde ejde e de ejd e e d eeje ejffd ZxZS) Olmo3Attentionconfig layer_idxct||||jJ|j||_|jdk(r|j|_yd|_y)N)rdr@)rCrDrFattention_typerErHrcrdrKs rLrDzOlmo3Attention.__init__s^ 95!!---$00;7;7J7JNa7af33gkrOr%position_embeddingsr&past_key_valuescache_positionrIreturnc |jdd}g|d|j}|j|j|} |j |j |} |j |} | j|jdd} | j|jdd} | j|jdd} |\} } t| | | | \} } |'| | |d}|j| | |j|\} } t}|jjdk7rt|jj}||| | | |f|j sdn |j"|j$|j&d|\}}|j(g|dj+}|j-|}||fS)Nr>r)sincosrjeagerrS)dropoutscalingrE)shapehead_dimq_normq_projk_normk_projv_projview transposerupdaterdrrc_attn_implementationrtrainingr<rrrEreshape contiguouso_proj)rHr%rhr&rirjrI input_shape hidden_shape query_states key_states value_statesrorn cache_kwargsattention_interface attn_output attn_weightss rLforwardzOlmo3Attention.forwards$))#2. 88b8$--8 {{4;;}#=> [[]!;< {{=1 #((6@@AF __\2<.)!. .) "% .) !!1!12 .)+,.) u||Xell33 4.)rOrbc eZdZy)Olmo3DecoderLayerNr_rBrOrLrr)r`rOrc$eZdZddedeefdZy)Olmo3RotaryEmbeddingNrc rope_typecVtjj||||_nht |drUt |j tr;|j jd|j jd|_nd|_|jJ|j|_ |j|_ ||_ t|j|_|j|j|\}|_|j!d|d|j"|_y)Nr:rtypedefaultinv_freqF) persistent)nnModulerDrhasattr isinstancer:dictgetr2max_seq_len_cachedoriginal_max_seq_lenrcr rope_init_fnattention_scalingregister_bufferroriginal_inv_freq)rHrcdevicerrs rLrDzOlmo3RotaryEmbedding.__init__0s 4  &DN V^ ,F)r)rc input_embedsr&rjrir)rAr@r@rAr)r&rrirjrh)last_hidden_staterirB) ValueErrorr'rrcget_seq_lengthrarangersr unsqueezerrr r rr(r. self_attnrfr)r )rHr#r&rrir$rjr4rIpast_seen_tokenscausal_mask_mapping mask_kwargsr%position_embeddings_mapping decoder_layers rLrzOlmo3Model.forward\s  -t"; <YZ Z  *.*;*;I*FM 0*$++>O  !CRC^==?de +0<< "2]5H5H5K"KTaThTh,N  )33A6L?-F++ -"0"0#2 , K#5"C{"C%F%U%U#  & !F!1!12E!F}Vb!c@d../?@P\]' # "[[)H4;;+H+HIM)2=3J3J3Y3YZ) /-$? @W@W@f@f$g MJ -0 &++  rO)NNNNNNN)rTrUrVrrDrrrrr FloatTensorboolrrr rr[r\s@rLrrMs {  151537+/5959$(C E,,-C !.C u//0 C "% C   1 12 C !!1!12C D>C +,C  !C rOrc eZdZy)Olmo3ForCausalLMNr_rBrOrLrrr`rOr)rrrr).typingrrrtorch.nnrtransformers.utils.genericr cache_utilsrrconfiguration_utilsr masking_utilsr r modeling_outputsr modeling_rope_utilsr rmodeling_utilsrprocessing_utilsrolmo2.configuration_olmo2rolmo2.modeling_olmo2rrrrrrrrrrr^rbrrrrr__all__rBrOrLrs & 9.8R7N5&3   |%+|%~ < 5)^5)p ) ///. / R R j '  rO