T^(h*ldZddlmZddlmZddlmZejeZ GddeZ dgZ y)zStarcoder2 model configuration)PretrainedConfig)rope_config_validation)loggingceZdZdZdZdgZdddddddZdgdgfd d gd gfd gd gfd Z d fd ZxZ S)Starcoder2Configa This is the configuration class to store the configuration of a [`Starcoder2Model`]. It is used to instantiate a Starcoder2 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 [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b) model. 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 49152): Vocabulary size of the Starcoder2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Starcoder2Model`] hidden_size (`int`, *optional*, defaults to 3072): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 12288): Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to 30): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 24): Number of attention heads for each attention layer in the Transformer encoder. num_key_value_heads (`int`, *optional*, defaults to 2): 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://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `8`. hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`): 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. Starcoder2's sliding window attention allows sequence of up to 4096*32 tokens. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. norm_epsilon (`float`, *optional*, defaults to 1e-05): Epsilon value for the layer norm 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`. bos_token_id (`int`, *optional*, defaults to 50256): The id of the "beginning-of-sequence" token. eos_token_id (`int`, *optional*, defaults to 50256): The id of the "end-of-sequence" token. 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 sliding_window (`int`, *optional*): Sliding window attention window size. If not specified, will default to `None` (no sliding window). attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. residual_dropout (`float`, *optional*, defaults to 0.0): Residual connection dropout value. embedding_dropout (`float`, *optional*, defaults to 0.0): Embedding dropout. use_bias (`bool`, *optional*, defaults to `True`): Whether to use bias term on linear layers of the model. ```python >>> from transformers import Starcoder2Model, Starcoder2Config >>> # Initializing a Starcoder2 7B style configuration >>> configuration = Starcoder2Config() >>> # Initializing a model from the Starcoder2 7B style configuration >>> model = Starcoder2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` starcoder2past_key_valuescolwiserowwise)zlayers.*.self_attn.q_projzlayers.*.self_attn.k_projzlayers.*.self_attn.v_projzlayers.*.self_attn.o_projzlayers.*.mlp.c_fczlayers.*.mlp.c_proj input_ids inputs_embeds hidden_statesattention_mask) embed_tokenslayersnormc ||_||_||_||_||_||_||_||_||_||_ | |_ | |_ | |_ ||_ ||_||_||_||_|j*d|jvr|jd|jd<t%|t'|Pd| | d|y)Ntype rope_type) bos_token_id eos_token_id) vocab_sizemax_position_embeddings hidden_sizeintermediate_sizenum_hidden_layersnum_attention_headssliding_windowuse_biasnum_key_value_heads hidden_actinitializer_range norm_epsilon use_cache rope_theta rope_scalingattention_dropoutresidual_dropoutembedding_dropoutrsuper__init__)selfrrrrrr!r"rr#r$r%rrr&r'rr(r)r*r kwargs __class__s u/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/starcoder2/configuration_starcoder2.pyr,zStarcoder2Config.__init__s0%'>$&!2!2#6 ,  #6 $!2("$(!2 0!2    (Vt7H7H-H-1->->v-FD  k *t$  %%  )ii i0gelu_pytorch_tanhigVy?gh㈵>TPr6g@NNr7r7T) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inferencebase_model_tp_planbase_model_pp_planr, __classcell__)r/s@r0rrsk ZJ#4"5&/%.%.%.&( &(9:#%568IJ!"_$56& $"+4 4 r1rN) r;configuration_utilsrmodeling_rope_utilsrutilsr get_loggerr8loggerr__all__rr1r0rGsA%39   H %s 's l  r1