fxmarty/tiny-mpt-random-remote-code

1"""A HuggingFace-style model configuration."""2from typing import Dict, Optional, Union3from transformers import PretrainedConfig4attn_config_defaults: Dict = {'attn_type': 'multihead_attention', 'attn_pdrop': 0.0, 'attn_impl': 'triton', 'qk_ln': False, 'clip_qkv': None, 'softmax_scale': None, 'prefix_lm': False, 'attn_uses_sequence_id': False, 'alibi': False, 'alibi_bias_max': 8}5init_config_defaults: Dict = {'name': 'kaiming_normal_', 'fan_mode': 'fan_in', 'init_nonlinearity': 'relu', 'init_div_is_residual': True, 'emb_init_std': None, 'emb_init_uniform_lim': None, 'init_std': None, 'init_gain': 0.0}6 7class MPTConfig(PretrainedConfig):8    model_type = 'mpt'9 10    def __init__(self, d_model: int=2048, n_heads: int=16, n_layers: int=24, expansion_ratio: int=4, max_seq_len: int=2048, vocab_size: int=50368, resid_pdrop: float=0.0, emb_pdrop: float=0.0, learned_pos_emb: bool=True, attn_config: Dict=attn_config_defaults, init_device: str='cpu', logit_scale: Optional[Union[float, str]]=None, no_bias: bool=False, verbose: int=0, embedding_fraction: float=1.0, norm_type: str='low_precision_layernorm', use_cache: bool=False, init_config: Dict=init_config_defaults, **kwargs):11        """The MPT configuration class.12 13        Args:14            d_model (int): The size of the embedding dimension of the model.15            n_heads (int): The number of attention heads.16            n_layers (int): The number of layers in the model.17            expansion_ratio (int): The ratio of the up/down scale in the MLP.18            max_seq_len (int): The maximum sequence length of the model.19            vocab_size (int): The size of the vocabulary.20            resid_pdrop (float): The dropout probability applied to the attention output before combining with residual.21            emb_pdrop (float): The dropout probability for the embedding layer.22            learned_pos_emb (bool): Whether to use learned positional embeddings23            attn_config (Dict):  A dictionary used to configure the model's attention module:24                attn_type (str): type of attention to use. Options: multihead_attention, multiquery_attention25                attn_pdrop (float): The dropout probability for the attention layers.26                attn_impl (str): The attention implementation to use. One of 'torch', 'flash', or 'triton'.27                qk_ln (bool): Whether to apply layer normalization to the queries and keys in the attention layer.28                clip_qkv (Optional[float]): If not None, clip the queries, keys, and values in the attention layer to29                    this value.30                softmax_scale (Optional[float]): If not None, scale the softmax in the attention layer by this value. If None,31                    use the default scale of ``1/sqrt(d_keys)``.32                prefix_lm (Optional[bool]): Whether the model should operate as a Prefix LM. This requires passing an33                    extra `prefix_mask` argument which indicates which tokens belong to the prefix. Tokens in the prefix34                    can attend to one another bi-directionally. Tokens outside the prefix use causal attention.35                attn_uses_sequence_id (Optional[bool]): Whether to restrict attention to tokens that have the same sequence_id.36                    When the model is in `train` mode, this requires passing an extra `sequence_id` argument which indicates37                    which sub-sequence each token belongs to.38                    Defaults to ``False`` meaning any provided `sequence_id` will be ignored.39                alibi (bool): Whether to use the alibi bias instead of position embeddings.40                alibi_bias_max (int): The maximum value of the alibi bias.41            init_device (str): The device to use for parameter initialization.42            logit_scale (Optional[Union[float, str]]): If not None, scale the logits by this value.43            no_bias (bool): Whether to use bias in all layers.44            verbose (int): The verbosity level. 0 is silent.45            embedding_fraction (float): The fraction to scale the gradients of the embedding layer by.46            norm_type (str): choose type of norm to use47            multiquery_attention (bool): Whether to use multiquery attention implementation.48            use_cache (bool): Whether or not the model should return the last key/values attentions49            init_config (Dict): A dictionary used to configure the model initialization:50                init_config.name: The parameter initialization scheme to use. Options: 'default_', 'baseline_',51                    'kaiming_uniform_', 'kaiming_normal_', 'neox_init_', 'small_init_', 'xavier_uniform_', or52                    'xavier_normal_'. These mimic the parameter initialization methods in PyTorch.53                init_div_is_residual (Union[int, float, str, bool]): Value to divide initial weights by if ``module._is_residual`` is True.54                emb_init_std (Optional[float]): The standard deviation of the normal distribution used to initialize the embedding layer.55                emb_init_uniform_lim (Optional[Union[Tuple[float, float], float]]): The lower and upper limits of the uniform distribution56                    used to initialize the embedding layer. Mutually exclusive with ``emb_init_std``.57                init_std (float): The standard deviation of the normal distribution used to initialize the model,58                    if using the baseline_ parameter initialization scheme.59                init_gain (float): The gain to use for parameter initialization with kaiming or xavier initialization schemes.60                fan_mode (str): The fan mode to use for parameter initialization with kaiming initialization schemes.61                init_nonlinearity (str): The nonlinearity to use for parameter initialization with kaiming initialization schemes.62                ---63                See llmfoundry.models.utils.param_init_fns.py for info on other param init config options64        """65        self.d_model = d_model66        self.n_heads = n_heads67        self.n_layers = n_layers68        self.expansion_ratio = expansion_ratio69        self.max_seq_len = max_seq_len70        self.vocab_size = vocab_size71        self.resid_pdrop = resid_pdrop72        self.emb_pdrop = emb_pdrop73        self.learned_pos_emb = learned_pos_emb74        self.attn_config = attn_config75        self.init_device = init_device76        self.logit_scale = logit_scale77        self.no_bias = no_bias78        self.verbose = verbose79        self.embedding_fraction = embedding_fraction80        self.norm_type = norm_type81        self.use_cache = use_cache82        self.init_config = init_config83        if 'name' in kwargs:84            del kwargs['name']85        if 'loss_fn' in kwargs:86            del kwargs['loss_fn']87        super().__init__(**kwargs)88        self._validate_config()89 90    def _set_config_defaults(self, config, config_defaults):91        for (k, v) in config_defaults.items():92            if k not in config:93                config[k] = v94        return config95 96    def _validate_config(self):97        self.attn_config = self._set_config_defaults(self.attn_config, attn_config_defaults)98        self.init_config = self._set_config_defaults(self.init_config, init_config_defaults)99        if self.d_model % self.n_heads != 0:100            raise ValueError('d_model must be divisible by n_heads')101        if any((prob < 0 or prob > 1 for prob in [self.attn_config['attn_pdrop'], self.resid_pdrop, self.emb_pdrop])):102            raise ValueError("self.attn_config['attn_pdrop'], resid_pdrop, emb_pdrop are probabilities and must be between 0 and 1")103        if self.attn_config['attn_impl'] not in ['torch', 'flash', 'triton']:104            raise ValueError(f"Unknown attn_impl={self.attn_config['attn_impl']}")105        if self.attn_config['prefix_lm'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:106            raise NotImplementedError('prefix_lm only implemented with torch and triton attention.')107        if self.attn_config['alibi'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:108            raise NotImplementedError('alibi only implemented with torch and triton attention.')109        if self.attn_config['attn_uses_sequence_id'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:110            raise NotImplementedError('attn_uses_sequence_id only implemented with torch and triton attention.')111        if self.embedding_fraction > 1 or self.embedding_fraction <= 0:112            raise ValueError('model.embedding_fraction must be between 0 (exclusive) and 1 (inclusive)!')113        if isinstance(self.logit_scale, str) and self.logit_scale != 'inv_sqrt_d_model':114            raise ValueError(f"self.logit_scale={self.logit_scale!r} is not recognized as an option; use numeric value or 'inv_sqrt_d_model'.")115        if self.init_config.get('name', None) is None:116            raise ValueError(f"self.init_config={self.init_config!r} 'name' needs to be set.")117        if not self.learned_pos_emb and (not self.attn_config['alibi']):118            raise ValueError(f'Positional information must be provided to the model using either learned_pos_emb or alibi.')