qi"ddZddlmZmZddlmZddlmZddlm Z m Z m Z m Z ddl mZejeZGd d eZGd d eZed Gdde Zed Gdde Zed Gdde Zed Gdde ZgdZy)zPyTorch Arcee model.)auto_docstringlogging)RopeParameters) LlamaConfig)LlamaForCausalLMLlamaForQuestionAnsweringLlamaForSequenceClassificationLlamaForTokenClassification) NemotronMLPc*<eZdZdZdZdddddddZ ddedzdedzd edzd edzd edzd edzd edzdedzdedzdedzde dzdedzdedzdedzde dzde e ee fzdzde dzdedzde dzdedzf(fd Z xZ S) ArceeConfiga This is the configuration class to store the configuration of a [`ArceeModel`]. It is used to instantiate an Arcee 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 AFM-4.5B-Base. Pre-trained weights are available at [arcee-ai/AFM-4.5B](https://huggingface.co/arcee-ai/AFM-4.5B) and were used to build the examples below. 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 32000): Vocabulary size of the Arcee model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ArceeModel`] hidden_size (`int`, *optional*, defaults to 2560): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 18432): 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 checkout [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 `"relu2"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 4096): The maximum sequence length that this model might ever be used with. AFM-4.5B-Base supports up to 16384 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*): Padding token id. bos_token_id (`int`, *optional*, defaults to 128000): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 128001): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `False`): Whether to tie weight embeddings rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. 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. mlp_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers. head_dim (`int`, *optional*): The attention head dimension. If None, it will default to hidden_size // num_attention_heads ```python >>> from transformers import ArceeModel, ArceeConfig >>> # Initializing an Arcee AFM-4.5B-Base style configuration >>> configuration = ArceeConfig() >>> # Initializing a model from the AFM-4.5B-Base style configuration >>> model = ArceeModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```arceecolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.up_projzlayers.*.mlp.down_projN 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_embeddingsrope_parametersattention_biasattention_dropoutmlp_biashead_dimc t|did|d|d|d|d|d|d|d|d | d | d | d | d | d|d|d|d|d|d|d|||`y)Nrrrrrrrrrrrrrr r!r"r#r$r%r&)super__init__pretraining_tp)selfrrrrrrrrrrrrrr r!r"r#r$r%r&kwargs __class__s Y/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/arcee/modular_arcee.pyr*zArceeConfig.__init__xs0  ! # 0 0  !4  !4  " %< 0 &   & & & !4 ,! "*# $0% &' (+ 0  )i}i iH r1Nrelu2ig{Gz?gh㈵>TNiiFNFgFN)__name__ __module__ __qualname____doc__ model_typebase_model_tp_planintstrfloatboolrdictr* __classcell__)r.s@r/rr sK ZJ%.%.%.%. )"+ "'"&(-(**,*.!(.2*.#'!%#'#)#)+0MQ&+*- %#+0 $J0 4Z0 : 0 : 0 !4Z 0 !4Z0 $J0 "%t0 !4<0 Dj0 $;0 Dj0 Dj0 Dj0 "D[!0 "($sN/B*CCdJ#0 $t %0 &!4<'0 (+)0 **+0 0 r0rc eZdZy)ArceeMLPNr3r4r5r(r0r/r@r@sr0r@zarcee-ai/AFM-4.5B) checkpointc eZdZy)ArceeForCausalLMNrAr(r0r/rDrDr0rDc eZdZy)ArceeForSequenceClassificationNrAr(r0r/rGrGrEr0rGc eZdZy)ArceeForQuestionAnsweringNrAr(r0r/rIrIrEr0rIc eZdZy)ArceeForTokenClassificationNrAr(r0r/rKrKrEr0rK)rrDrIrGrK ArceeModelArceePreTrainedModelN)r6transformers.utilsrrmodeling_rope_utilsrllama.configuration_llamarllama.modeling_llamar r r r nemotron.modeling_nemotronr get_loggerr3loggerrr@rDrGrIrK__all__r(r0r/rVs613 5   H %H +H V { ./ ' 0 ./ %C 0 ./ 9 0 ./ "= 0  r0