phi3

mindnlp.transformers.models.phi3.configuration_phi3

Phi-3 model configuration

mindnlp.transformers.models.phi3.configuration_phi3.Phi3Config

Bases: PretrainedConfig

This is the configuration class to store the configuration of a [Phi3Model]. It is used to instantiate a Phi-3 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 microsoft/Phi-3-mini-4k-instruct.

Configuration objects inherit from [PretrainedConfig] and can be used to control the model outputs. Read the documentation from [PretrainedConfig] for more information.

PARAMETER	DESCRIPTION
vocab_size	Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [Phi3Model]. TYPE: `int`, *optional*, defaults to 32064 DEFAULT: 32064
hidden_size	Dimension of the hidden representations. TYPE: `int`, *optional*, defaults to 3072 DEFAULT: 3072
intermediate_size	Dimension of the MLP representations. TYPE: `int`, *optional*, defaults to 8192 DEFAULT: 8192
num_hidden_layers	Number of hidden layers in the Transformer decoder. TYPE: `int`, *optional*, defaults to 32 DEFAULT: 32
num_attention_heads	Number of attention heads for each attention layer in the Transformer decoder. TYPE: `int`, *optional*, defaults to 32 DEFAULT: 32
num_key_value_heads	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. If it is not specified, will default to num_attention_heads. TYPE: `int`, *optional* DEFAULT: None
resid_pdrop	Dropout probability for mlp outputs. TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0
embd_pdrop	The dropout ratio for the embeddings. TYPE: `int`, *optional*, defaults to 0.0 DEFAULT: 0.0
attention_dropout	The dropout ratio after computing the attention scores. TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0
hidden_act	The non-linear activation function (function or string) in the decoder. TYPE: `str` or `function`, *optional*, defaults to `"silu"` DEFAULT: 'silu'
max_position_embeddings	The maximum sequence length that this model might ever be used with. TYPE: `int`, *optional*, defaults to 4096 DEFAULT: 4096
original_max_position_embeddings	The maximum sequence length that this model was trained with. This is used to determine the size of the original RoPE embeddings when using long scaling. TYPE: `int`, *optional*, defaults to 4096 DEFAULT: 4096
initializer_range	The standard deviation of the truncated_normal_initializer for initializing all weight matrices. TYPE: `float`, *optional*, defaults to 0.02 DEFAULT: 0.02
rms_norm_eps	The epsilon value used for the RMSNorm. TYPE: `float`, *optional*, defaults to 1e-05 DEFAULT: 1e-05
use_cache	Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True. Whether to tie weight embeddings or not. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
tie_word_embeddings	Whether to tie weight embeddings TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
rope_theta	The base period of the RoPE embeddings. TYPE: `float`, *optional*, defaults to 10000.0 DEFAULT: 10000.0
rope_scaling	The scaling strategy for the RoPE embeddings. If None, no scaling is applied. If a dictionary, it must contain the following keys: type, short_factor and long_factor. The type must be longrope and the short_factor and long_factor must be lists of numbers with the same length as the hidden size divided by the number of attention heads divided by 2. TYPE: `dict`, *optional* DEFAULT: None
bos_token_id	The id of the "beginning-of-sequence" token. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
eos_token_id	The id of the "end-of-sequence" token. TYPE: `int`, *optional*, defaults to 32000 DEFAULT: 32000
pad_token_id	The id of the padding token. TYPE: `int`, *optional*, defaults to 32000 DEFAULT: 32000
sliding_window	Sliding window attention window size. If None, no sliding window is applied. TYPE: `int`, *optional* DEFAULT: None

>>> from transformers import Phi3Model, Phi3Config

>>> # Initializing a Phi-3 style configuration
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")

>>> # Initializing a model from the configuration
>>> model = Phi3Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

Source code in mindnlp\transformers\models\phi3\configuration_phi3.py

class Phi3Config(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
    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
    [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).

    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 32064):
            Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`Phi3Model`].
        hidden_size (`int`, *optional*, defaults to 3072):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 8192):
            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://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
            `num_attention_heads`.
        resid_pdrop (`float`, *optional*, defaults to 0.0):
            Dropout probability for mlp outputs.
        embd_pdrop (`int`, *optional*, defaults to 0.0):
            The dropout ratio for the embeddings.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio after computing the attention scores.
        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 4096):
            The maximum sequence length that this model might ever be used with.
        original_max_position_embeddings (`int`, *optional*, defaults to 4096):
            The maximum sequence length that this model was trained with. This is used to determine the size of the
            original RoPE embeddings when using long scaling.
        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 value used for the RMSNorm.
        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`. Whether to tie weight embeddings or not.
        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*):
            The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
            contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
            the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
            divided by the number of attention heads divided by 2.
        bos_token_id (`int`, *optional*, defaults to 1):
            The id of the "beginning-of-sequence" token.
        eos_token_id (`int`, *optional*, defaults to 32000):
            The id of the "end-of-sequence" token.
        pad_token_id (`int`, *optional*, defaults to 32000):
            The id of the padding token.
        sliding_window (`int`, *optional*):
            Sliding window attention window size. If `None`, no sliding window is applied.

    Example:

    ```python
    >>> from transformers import Phi3Model, Phi3Config

    >>> # Initializing a Phi-3 style configuration
    >>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")

    >>> # Initializing a model from the configuration
    >>> model = Phi3Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "phi3"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=32064,
        hidden_size=3072,
        intermediate_size=8192,
        num_hidden_layers=32,
        num_attention_heads=32,
        num_key_value_heads=None,
        resid_pdrop=0.0,
        embd_pdrop=0.0,
        attention_dropout=0.0,
        hidden_act="silu",
        max_position_embeddings=4096,
        original_max_position_embeddings=4096,
        initializer_range=0.02,
        rms_norm_eps=1e-5,
        use_cache=True,
        tie_word_embeddings=False,
        rope_theta=10000.0,
        rope_scaling=None,
        bos_token_id=1,
        eos_token_id=32000,
        pad_token_id=32000,
        sliding_window=None,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads

        if num_key_value_heads is None:
            num_key_value_heads = num_attention_heads

        self.num_key_value_heads = num_key_value_heads
        self.resid_pdrop = resid_pdrop
        self.embd_pdrop = embd_pdrop
        self.attention_dropout = attention_dropout
        self.hidden_act = hidden_act
        self.max_position_embeddings = max_position_embeddings
        self.original_max_position_embeddings = original_max_position_embeddings
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self._rope_scaling_adjustment()
        self._rope_scaling_validation()
        self.sliding_window = sliding_window

        super().__init__(
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            pad_token_id=pad_token_id,
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )

    def _rope_scaling_adjustment(self):
        """
        Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
        """
        if self.rope_scaling is None:
            return

        rope_scaling_type = self.rope_scaling.get("type", None)

        # For backward compatibility if previous version used "su" or "yarn"
        if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
            self.rope_scaling["type"] = "longrope"

    def _rope_scaling_validation(self):
        """
        Validate the `rope_scaling` configuration.
        """
        if self.rope_scaling is None:
            return

        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
            raise ValueError(
                "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
                f"got {self.rope_scaling}"
            )
        rope_scaling_type = self.rope_scaling.get("type", None)
        rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
        rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
        if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
            raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
        if not (
            isinstance(rope_scaling_short_factor, list)
            and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
        ):
            raise ValueError(
                f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
            )
        if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
            raise ValueError(
                f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
            )
        if not (
            isinstance(rope_scaling_long_factor, list)
            and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
        ):
            raise ValueError(
                f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
            )
        if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
            raise ValueError(
                f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
            )

mindnlp.transformers.models.phi3.modeling_phi3

MindSpore Phi-3 model.

mindnlp.transformers.models.phi3.modeling_phi3.Phi3Attention

Bases: Module

Multi-headed attention from 'Attention Is All You Need' paper

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

class Phi3Attention(nn.Module):
    """Multi-headed attention from 'Attention Is All You Need' paper"""

    def __init__(self, config: Phi3Config, layer_idx: Optional[int] = None):
        super().__init__()
        self.config = config
        self.layer_idx = layer_idx
        if layer_idx is None:
            logger.warning_once(
                f"Instantiating {self.__class__.__name__} without passing a `layer_idx` is not recommended and will "
                "lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` "
                "when creating this class."
            )

        self.attention_dropout = config.attention_dropout
        self.hidden_size = config.hidden_size
        self.num_heads = config.num_attention_heads
        self.head_dim = self.hidden_size // self.num_heads
        self.num_key_value_heads = config.num_key_value_heads
        self.num_key_value_groups = self.num_heads // self.num_key_value_heads
        self.max_position_embeddings = config.max_position_embeddings
        self.original_max_position_embeddings = config.original_max_position_embeddings
        self.rope_theta = config.rope_theta
        self.rope_scaling = config.rope_scaling
        self.is_causal = True

        if (self.head_dim * self.num_heads) != self.hidden_size:
            raise ValueError(
                f"hidden_size must be divisible by num_heads (got `hidden_size`: {self.hidden_size}"
                f" and `num_heads`: {self.num_heads})."
            )

        op_size = self.num_heads * self.head_dim + 2 * (self.num_key_value_heads * self.head_dim)
        self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False)
        self.qkv_proj = nn.Linear(self.hidden_size, op_size, bias=False)
        self._init_rope()

    def _init_rope(self):
        if self.rope_scaling is None:
            self.rotary_emb = Phi3RotaryEmbedding(
                self.head_dim,
                max_position_embeddings=self.max_position_embeddings,
                base=self.rope_theta,
            )
        else:
            scaling_type = self.config.rope_scaling["type"]
            if scaling_type == "longrope":
                self.rotary_emb = Phi3LongRoPEScaledRotaryEmbedding(self.head_dim, self.config)
            else:
                raise ValueError(f"Unknown RoPE scaling type {scaling_type}")

    def forward(
        self,
        hidden_states: mindspore.Tensor,
        attention_mask: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        past_key_value: Optional[Cache] = None,
        output_attentions: bool = False,
        use_cache: bool = False,
        cache_position: Optional[mindspore.Tensor] = None,
    ) -> Tuple[mindspore.Tensor, Optional[mindspore.Tensor], Optional[Tuple[mindspore.Tensor]]]:
        logger.warning_once("You are not running the flash-attention implementation, expect numerical differences.")

        bsz, q_len, _ = hidden_states.shape

        qkv = self.qkv_proj(hidden_states)
        query_pos = self.num_heads * self.head_dim
        query_states = qkv[..., :query_pos]
        key_states = qkv[..., query_pos : query_pos + self.num_key_value_heads * self.head_dim]
        value_states = qkv[..., query_pos + self.num_key_value_heads * self.head_dim :]

        query_states = ops.transpose(query_states.view(bsz, q_len, self.num_heads, self.head_dim), 1, 2)
        key_states = ops.transpose(key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim), 1, 2)
        value_states = ops.transpose(value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim), 1, 2)

        kv_seq_len = key_states.shape[-2]
        if past_key_value is not None:
            if self.layer_idx is None:
                raise ValueError(
                    f"The cache structure has changed since version v4.36. If you are using {self.__class__.__name__} "
                    "for auto-regressive decoding with k/v caching, please make sure to initialize the attention class "
                    "with a layer index."
                )
            kv_seq_len += past_key_value.get_usable_length(kv_seq_len, self.layer_idx)
        cos, sin = self.rotary_emb(value_states, position_ids, seq_len=kv_seq_len)

        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)

        if past_key_value is not None:
            cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}  # Specific to RoPE models
            key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)

        # repeat k/v heads if n_kv_heads < n_heads
        key_states = repeat_kv(key_states, self.num_key_value_groups)
        value_states = repeat_kv(value_states, self.num_key_value_groups)

        attn_weights = ops.matmul(query_states, ops.transpose(key_states, 2, 3)) / math.sqrt(self.head_dim)

        if attention_mask is not None:
            causal_mask = attention_mask[:, :, :, : key_states.shape[-2]]
            attn_weights += causal_mask

        # upcast attention to fp32
        attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=mindspore.float32).to(value_states.dtype)
        attn_weights = nn.functional.dropout(attn_weights, p=self.attention_dropout, training=self.training)

        attn_output = ops.matmul(attn_weights, value_states)

        if attn_output.shape != (bsz, self.num_heads, q_len, self.head_dim):
            raise ValueError(
                f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
                f" {attn_output.shape}"
            )

        attn_output = ops.transpose(attn_output, 1, 2)
        attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)

        attn_output = self.o_proj(attn_output)

        if not output_attentions:
            attn_weights = None

        return attn_output, attn_weights, past_key_value

mindnlp.transformers.models.phi3.modeling_phi3.Phi3DecoderLayer

Bases: Module

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

class Phi3DecoderLayer(nn.Module):
    def __init__(self, config: Phi3Config, layer_idx: int):
        super().__init__()

        self.config = config
        self.self_attn = PHI3_ATTENTION_CLASSES[config._attn_implementation](config, layer_idx=layer_idx)

        self.mlp = Phi3MLP(config)
        self.input_layernorm = Phi3RMSNorm(config.hidden_size, eps=config.rms_norm_eps)

        self.resid_attn_dropout = nn.Dropout(config.resid_pdrop)
        self.resid_mlp_dropout = nn.Dropout(config.resid_pdrop)
        self.post_attention_layernorm = Phi3RMSNorm(config.hidden_size, eps=config.rms_norm_eps)

    def forward(
        self,
        hidden_states: mindspore.Tensor,
        attention_mask: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        past_key_value: Optional[Tuple[mindspore.Tensor]] = None,
        output_attentions: Optional[bool] = False,
        use_cache: Optional[bool] = False,
        cache_position: Optional[mindspore.Tensor] = None,
        **kwargs,
    ) -> Tuple[mindspore.Tensor, Optional[Tuple[mindspore.Tensor, mindspore.Tensor]]]:
        """
        Args:
            hidden_states (`mindspore.Tensor`):
                input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`mindspore.Tensor`, *optional*): attention mask of size
                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
            position_ids (`mindspore.Tensor` of shape `({0})`, *optional*):
                Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
                `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids)
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see `past_key_values`).
            past_key_value (`Tuple(mindspore.Tensor)`, *optional*): cached past key and value projection states
            cache_position (`mindspore.Tensor` of shape `(sequence_length)`, *optional*):
                Indices depicting the position of the input sequence tokens in the sequence
            kwargs (`dict`, *optional*):
                Arbitrary kwargs to be ignored, used for FSDP and other methods that injects code
                into the model
        """

        residual = hidden_states

        hidden_states = self.input_layernorm(hidden_states)

        # Self Attention
        attn_outputs, self_attn_weights, present_key_value = self.self_attn(
            hidden_states=hidden_states,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_value=past_key_value,
            output_attentions=output_attentions,
            use_cache=use_cache,
            cache_position=cache_position,
        )

        hidden_states = residual + self.resid_attn_dropout(attn_outputs)

        residual = hidden_states
        hidden_states = self.post_attention_layernorm(hidden_states)
        hidden_states = self.mlp(hidden_states)
        hidden_states = residual + self.resid_mlp_dropout(hidden_states)

        outputs = (hidden_states,)

        if output_attentions:
            outputs += (self_attn_weights,)

        if use_cache:
            outputs += (present_key_value,)

        return outputs

mindnlp.transformers.models.phi3.modeling_phi3.Phi3DecoderLayer.forward(hidden_states, attention_mask=None, position_ids=None, past_key_value=None, output_attentions=False, use_cache=False, cache_position=None, **kwargs)

PARAMETER	DESCRIPTION
hidden_states	input to the layer of shape (batch, seq_len, embed_dim) TYPE: `mindspore.Tensor`
attention_mask	attention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values. TYPE: `mindspore.Tensor`, *optional* DEFAULT: None
position_ids	Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1]. What are position IDs? TYPE: `mindspore.Tensor` of shape `({0})`, *optional* DEFAULT: None
output_attentions	Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail. TYPE: `bool`, *optional* DEFAULT: False
use_cache	If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values). TYPE: `bool`, *optional* DEFAULT: False
past_key_value	cached past key and value projection states TYPE: `Tuple(mindspore.Tensor)`, *optional* DEFAULT: None
cache_position	Indices depicting the position of the input sequence tokens in the sequence TYPE: `mindspore.Tensor` of shape `(sequence_length)`, *optional* DEFAULT: None
kwargs	Arbitrary kwargs to be ignored, used for FSDP and other methods that injects code into the model TYPE: `dict`, *optional* DEFAULT: {}

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def forward(
    self,
    hidden_states: mindspore.Tensor,
    attention_mask: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    past_key_value: Optional[Tuple[mindspore.Tensor]] = None,
    output_attentions: Optional[bool] = False,
    use_cache: Optional[bool] = False,
    cache_position: Optional[mindspore.Tensor] = None,
    **kwargs,
) -> Tuple[mindspore.Tensor, Optional[Tuple[mindspore.Tensor, mindspore.Tensor]]]:
    """
    Args:
        hidden_states (`mindspore.Tensor`):
            input to the layer of shape `(batch, seq_len, embed_dim)`
        attention_mask (`mindspore.Tensor`, *optional*): attention mask of size
            `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
        position_ids (`mindspore.Tensor` of shape `({0})`, *optional*):
            Indices of positions of each input sequence tokens in the position embeddings. Selected in the range
            `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids)
        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under
            returned tensors for more detail.
        use_cache (`bool`, *optional*):
            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
            (see `past_key_values`).
        past_key_value (`Tuple(mindspore.Tensor)`, *optional*): cached past key and value projection states
        cache_position (`mindspore.Tensor` of shape `(sequence_length)`, *optional*):
            Indices depicting the position of the input sequence tokens in the sequence
        kwargs (`dict`, *optional*):
            Arbitrary kwargs to be ignored, used for FSDP and other methods that injects code
            into the model
    """

    residual = hidden_states

    hidden_states = self.input_layernorm(hidden_states)

    # Self Attention
    attn_outputs, self_attn_weights, present_key_value = self.self_attn(
        hidden_states=hidden_states,
        attention_mask=attention_mask,
        position_ids=position_ids,
        past_key_value=past_key_value,
        output_attentions=output_attentions,
        use_cache=use_cache,
        cache_position=cache_position,
    )

    hidden_states = residual + self.resid_attn_dropout(attn_outputs)

    residual = hidden_states
    hidden_states = self.post_attention_layernorm(hidden_states)
    hidden_states = self.mlp(hidden_states)
    hidden_states = residual + self.resid_mlp_dropout(hidden_states)

    outputs = (hidden_states,)

    if output_attentions:
        outputs += (self_attn_weights,)

    if use_cache:
        outputs += (present_key_value,)

    return outputs

mindnlp.transformers.models.phi3.modeling_phi3.Phi3ForCausalLM

Bases: Phi3PreTrainedModel

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

class Phi3ForCausalLM(Phi3PreTrainedModel):
    _tied_weights_keys = ["lm_head.weight"]

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.__init__ with Llama->Phi3
    def __init__(self, config):
        super().__init__(config)
        self.model = Phi3Model(config)
        self.vocab_size = config.vocab_size
        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)

        # Initialize weights and apply final processing
        self.post_init()

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.get_input_embeddings
    def get_input_embeddings(self):
        return self.model.embed_tokens

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.set_input_embeddings
    def set_input_embeddings(self, value):
        self.model.embed_tokens = value

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.get_output_embeddings
    def get_output_embeddings(self):
        return self.lm_head

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.set_output_embeddings
    def set_output_embeddings(self, new_embeddings):
        self.lm_head = new_embeddings

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.set_decoder
    def set_decoder(self, decoder):
        self.model = decoder

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.get_decoder
    def get_decoder(self):
        return self.model

    # Ignore copy
    def forward(
        self,
        input_ids: mindspore.Tensor = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[List[mindspore.Tensor]] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        cache_position: Optional[mindspore.Tensor] = None,
    ) -> Union[Tuple, CausalLMOutputWithPast]:
        r"""
        Args:
            labels (`mindspore.Tensor` 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]`.

        Returns:

        Example:

        ```python
        >>> from transformers import AutoTokenizer, Phi3ForCausalLM

        >>> model = Phi3ForCausalLM.from_pretrained("microsoft/phi-3-mini-4k-instruct")
        >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-3-mini-4k-instruct")

        >>> prompt = "This is an example script ."
        >>> inputs = tokenizer(prompt, return_tensors="ms")

        >>> # 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]
        'This is an example script .\n Certainly! Below is a sample script that demonstrates a simple task, such as calculating the sum'
        ```"""

        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
        outputs = self.model(
            input_ids=input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        hidden_states = outputs[0]
        logits = self.lm_head(hidden_states)
        logits = logits.float()

        loss = None
        if labels is not None:
            # Shift so that tokens < n predict n
            shift_logits = logits[..., :-1, :]
            shift_labels = labels[..., 1:]
            # Flatten the tokens
            loss_fct = CrossEntropyLoss()
            shift_logits = shift_logits.view(-1, self.config.vocab_size)
            shift_labels = shift_labels.view(-1)
            # Enable model parallelism
            loss = loss_fct(shift_logits, shift_labels)

        if not return_dict:
            output = (logits,) + outputs[1:]
            return (loss,) + output if loss is not None else output

        return CausalLMOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

    # Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM.prepare_inputs_for_generation
    def prepare_inputs_for_generation(
        self,
        input_ids,
        past_key_values=None,
        attention_mask=None,
        inputs_embeds=None,
        cache_position=None,
        position_ids=None,
        use_cache=True,
        **kwargs,
    ):
        # If we have cache: let's slice `input_ids` through `cache_position`, to keep only the unprocessed tokens
        # Exception 1: when passing input_embeds, input_ids may be missing entries
        # Exception 2: some generation methods do special slicing of input_ids, so we don't need to do it here
        if past_key_values is not None:
            if inputs_embeds is not None:  # Exception 1
                if 0 not in input_ids.shape:
                    input_ids = input_ids[:, -cache_position.shape[0] :]
            elif input_ids.shape[1] != cache_position.shape[0]:  # Default case (the "else", a no op, is Exception 2)
                input_ids = input_ids[:, cache_position]

        if attention_mask is not None and position_ids is None:
            # create position_ids on the fly for batch generation
            position_ids = attention_mask.int().cumsum(-1) - 1
            position_ids = position_ids.masked_fill(attention_mask == 0, 1)
            if past_key_values:
                position_ids = position_ids[:, -input_ids.shape[1] :]


        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
        if inputs_embeds is not None and cache_position[0] == 0:
            model_inputs = {"inputs_embeds": inputs_embeds, "input_ids": None}
        else:
            # The clone here is for the same reason as for `position_ids`.
            model_inputs = {"input_ids": input_ids, "inputs_embeds": None}

        if isinstance(past_key_values, StaticCache) and attention_mask.ndim == 2:
            if model_inputs["inputs_embeds"] is not None:
                batch_size, sequence_length, _ = model_inputs["inputs_embeds"].shape
            else:
                batch_size, sequence_length = model_inputs["input_ids"].shape

            dtype = self.lm_head.weight.dtype
            min_dtype = float(ops.finfo(dtype).min)

            attention_mask = _prepare_4d_causal_attention_mask_with_cache_position(
                attention_mask,
                sequence_length=sequence_length,
                target_length=past_key_values.get_max_length(),
                dtype=dtype,
                min_dtype=min_dtype,
                cache_position=cache_position,
                batch_size=batch_size,
            )

        model_inputs.update(
            {
                "position_ids": position_ids,
                "cache_position": cache_position,
                "past_key_values": past_key_values,
                "use_cache": use_cache,
                "attention_mask": attention_mask,
            }
        )
        return model_inputs

mindnlp.transformers.models.phi3.modeling_phi3.Phi3ForCausalLM.forward(input_ids=None, attention_mask=None, position_ids=None, past_key_values=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, cache_position=None)

PARAMETER	DESCRIPTION
labels	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]. TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

Example:

>>> from transformers import AutoTokenizer, Phi3ForCausalLM

>>> model = Phi3ForCausalLM.from_pretrained("microsoft/phi-3-mini-4k-instruct")
>>> tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-3-mini-4k-instruct")

>>> prompt = "This is an example script ."
>>> inputs = tokenizer(prompt, return_tensors="ms")

>>> # 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]
'This is an example script .\n Certainly! Below is a sample script that demonstrates a simple task, such as calculating the sum'

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def forward(
    self,
    input_ids: mindspore.Tensor = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    past_key_values: Optional[List[mindspore.Tensor]] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
    cache_position: Optional[mindspore.Tensor] = None,
) -> Union[Tuple, CausalLMOutputWithPast]:
    r"""
    Args:
        labels (`mindspore.Tensor` 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]`.

    Returns:

    Example:

    ```python
    >>> from transformers import AutoTokenizer, Phi3ForCausalLM

    >>> model = Phi3ForCausalLM.from_pretrained("microsoft/phi-3-mini-4k-instruct")
    >>> tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-3-mini-4k-instruct")

    >>> prompt = "This is an example script ."
    >>> inputs = tokenizer(prompt, return_tensors="ms")

    >>> # 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]
    'This is an example script .\n Certainly! Below is a sample script that demonstrates a simple task, such as calculating the sum'
    ```"""

    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
    outputs = self.model(
        input_ids=input_ids,
        attention_mask=attention_mask,
        position_ids=position_ids,
        past_key_values=past_key_values,
        inputs_embeds=inputs_embeds,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    hidden_states = outputs[0]
    logits = self.lm_head(hidden_states)
    logits = logits.float()

    loss = None
    if labels is not None:
        # Shift so that tokens < n predict n
        shift_logits = logits[..., :-1, :]
        shift_labels = labels[..., 1:]
        # Flatten the tokens
        loss_fct = CrossEntropyLoss()
        shift_logits = shift_logits.view(-1, self.config.vocab_size)
        shift_labels = shift_labels.view(-1)
        # Enable model parallelism
        loss = loss_fct(shift_logits, shift_labels)

    if not return_dict:
        output = (logits,) + outputs[1:]
        return (loss,) + output if loss is not None else output

    return CausalLMOutputWithPast(
        loss=loss,
        logits=logits,
        past_key_values=outputs.past_key_values,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.phi3.modeling_phi3.Phi3ForSequenceClassification

Bases: Phi3PreTrainedModel

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

class Phi3ForSequenceClassification(Phi3PreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.model = Phi3Model(config)
        self.score = nn.Linear(config.hidden_size, self.num_labels, bias=False)

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.model.embed_tokens

    def set_input_embeddings(self, value):
        self.model.embed_tokens = value

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[Union[Cache, List[mindspore.Tensor]]] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, SequenceClassifierOutputWithPast]:
        r"""
        labels (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        model_outputs = self.model(
            input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        hidden_states = model_outputs[0]
        logits = self.score(hidden_states)

        if input_ids is not None:
            batch_size = input_ids.shape[0]
        else:
            batch_size = inputs_embeds.shape[0]

        if self.config.pad_token_id is None and batch_size != 1:
            raise ValueError("Cannot handle batch sizes > 1 if no padding token is defined.")
        if self.config.pad_token_id is None:
            sequence_lengths = -1
        else:
            if input_ids is not None:
                # if no pad token found, use modulo instead of reverse indexing for ONNX compatibility
                sequence_lengths = ops.eq(input_ids, self.config.pad_token_id).int().argmax(-1) - 1
                sequence_lengths = sequence_lengths % input_ids.shape[-1]
            else:
                sequence_lengths = -1

        pooled_logits = logits[ops.arange(batch_size), sequence_lengths]

        loss = None
        if labels is not None:
            if self.config.problem_type is None:
                if self.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.num_labels > 1 and labels.dtype in (mindspore.int64, mindspore.int32):
                    self.config.problem_type = "single_label_classification"
                else:
                    self.config.problem_type = "multi_label_classification"

            if self.config.problem_type == "regression":
                loss_fct = MSELoss()
                if self.num_labels == 1:
                    loss = loss_fct(pooled_logits.squeeze(), labels.squeeze())
                else:
                    loss = loss_fct(pooled_logits, labels)
            elif self.config.problem_type == "single_label_classification":
                loss_fct = CrossEntropyLoss()
                loss = loss_fct(pooled_logits.view(-1, self.num_labels), labels.view(-1))
            elif self.config.problem_type == "multi_label_classification":
                loss_fct = BCEWithLogitsLoss()
                loss = loss_fct(pooled_logits, labels)
        if not return_dict:
            output = (pooled_logits,) + model_outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return SequenceClassifierOutputWithPast(
            loss=loss,
            logits=pooled_logits,
            past_key_values=model_outputs.past_key_values,
            hidden_states=model_outputs.hidden_states,
            attentions=model_outputs.attentions,
        )

mindnlp.transformers.models.phi3.modeling_phi3.Phi3ForSequenceClassification.forward(input_ids=None, attention_mask=None, position_ids=None, past_key_values=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

labels (mindspore.Tensor of shape (batch_size,), optional): Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    past_key_values: Optional[Union[Cache, List[mindspore.Tensor]]] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, SequenceClassifierOutputWithPast]:
    r"""
    labels (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
        Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
        config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
        `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
    """
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    model_outputs = self.model(
        input_ids,
        attention_mask=attention_mask,
        position_ids=position_ids,
        past_key_values=past_key_values,
        inputs_embeds=inputs_embeds,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )
    hidden_states = model_outputs[0]
    logits = self.score(hidden_states)

    if input_ids is not None:
        batch_size = input_ids.shape[0]
    else:
        batch_size = inputs_embeds.shape[0]

    if self.config.pad_token_id is None and batch_size != 1:
        raise ValueError("Cannot handle batch sizes > 1 if no padding token is defined.")
    if self.config.pad_token_id is None:
        sequence_lengths = -1
    else:
        if input_ids is not None:
            # if no pad token found, use modulo instead of reverse indexing for ONNX compatibility
            sequence_lengths = ops.eq(input_ids, self.config.pad_token_id).int().argmax(-1) - 1
            sequence_lengths = sequence_lengths % input_ids.shape[-1]
        else:
            sequence_lengths = -1

    pooled_logits = logits[ops.arange(batch_size), sequence_lengths]

    loss = None
    if labels is not None:
        if self.config.problem_type is None:
            if self.num_labels == 1:
                self.config.problem_type = "regression"
            elif self.num_labels > 1 and labels.dtype in (mindspore.int64, mindspore.int32):
                self.config.problem_type = "single_label_classification"
            else:
                self.config.problem_type = "multi_label_classification"

        if self.config.problem_type == "regression":
            loss_fct = MSELoss()
            if self.num_labels == 1:
                loss = loss_fct(pooled_logits.squeeze(), labels.squeeze())
            else:
                loss = loss_fct(pooled_logits, labels)
        elif self.config.problem_type == "single_label_classification":
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(pooled_logits.view(-1, self.num_labels), labels.view(-1))
        elif self.config.problem_type == "multi_label_classification":
            loss_fct = BCEWithLogitsLoss()
            loss = loss_fct(pooled_logits, labels)
    if not return_dict:
        output = (pooled_logits,) + model_outputs[1:]
        return ((loss,) + output) if loss is not None else output

    return SequenceClassifierOutputWithPast(
        loss=loss,
        logits=pooled_logits,
        past_key_values=model_outputs.past_key_values,
        hidden_states=model_outputs.hidden_states,
        attentions=model_outputs.attentions,
    )

mindnlp.transformers.models.phi3.modeling_phi3.Phi3ForTokenClassification

Bases: Phi3PreTrainedModel

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

class Phi3ForTokenClassification(Phi3PreTrainedModel):
    def __init__(self, config: Phi3Config):
        super().__init__(config)
        self.num_labels = config.num_labels

        self.model = Phi3Model(config)
        if hasattr(config, "classifier_dropout") and config.classifier_dropout is not None:
            classifier_dropout = config.classifier_dropout
        elif hasattr(config, "hidden_dropout") and config.hidden_dropout is not None:
            classifier_dropout = config.hidden_dropout
        else:
            classifier_dropout = 0.1
        self.dropout = nn.Dropout(classifier_dropout)
        self.classifier = nn.Linear(config.hidden_size, config.num_labels)

        # Initialize weights and apply final processing
        self.post_init()

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[Tuple[Tuple[mindspore.Tensor, mindspore.Tensor], ...]] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        **deprecated_arguments,
    ) -> Union[Tuple[mindspore.Tensor], TokenClassifierOutput]:
        r"""
        labels (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        model_outputs = self.model(
            input_ids,
            past_key_values=past_key_values,
            attention_mask=attention_mask,
            inputs_embeds=inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        hidden_states = model_outputs[0]
        hidden_states = self.dropout(hidden_states)
        logits = self.classifier(hidden_states)

        loss = None
        if labels is not None:
            batch_size, seq_length = labels.shape
            loss_fct = CrossEntropyLoss()
            loss = loss_fct(
                logits.view(batch_size * seq_length, self.num_labels), labels.view(batch_size * seq_length)
            )

        if not return_dict:
            output = (logits,) + model_outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return TokenClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=model_outputs.hidden_states,
            attentions=model_outputs.attentions,
        )

mindnlp.transformers.models.phi3.modeling_phi3.Phi3ForTokenClassification.forward(input_ids=None, past_key_values=None, attention_mask=None, inputs_embeds=None, labels=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None, **deprecated_arguments)

labels (mindspore.Tensor of shape (batch_size,), optional): Labels for computing the sequence classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    past_key_values: Optional[Tuple[Tuple[mindspore.Tensor, mindspore.Tensor], ...]] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
    **deprecated_arguments,
) -> Union[Tuple[mindspore.Tensor], TokenClassifierOutput]:
    r"""
    labels (`mindspore.Tensor` of shape `(batch_size,)`, *optional*):
        Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
        config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
        `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
    """
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    model_outputs = self.model(
        input_ids,
        past_key_values=past_key_values,
        attention_mask=attention_mask,
        inputs_embeds=inputs_embeds,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    hidden_states = model_outputs[0]
    hidden_states = self.dropout(hidden_states)
    logits = self.classifier(hidden_states)

    loss = None
    if labels is not None:
        batch_size, seq_length = labels.shape
        loss_fct = CrossEntropyLoss()
        loss = loss_fct(
            logits.view(batch_size * seq_length, self.num_labels), labels.view(batch_size * seq_length)
        )

    if not return_dict:
        output = (logits,) + model_outputs[2:]
        return ((loss,) + output) if loss is not None else output

    return TokenClassifierOutput(
        loss=loss,
        logits=logits,
        hidden_states=model_outputs.hidden_states,
        attentions=model_outputs.attentions,
    )

mindnlp.transformers.models.phi3.modeling_phi3.Phi3Model

Bases: Phi3PreTrainedModel

Transformer decoder consisting of config.num_hidden_layers layers. Each layer is a [Phi3DecoderLayer]

PARAMETER	DESCRIPTION
config	Phi3Config TYPE: Phi3Config

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

class Phi3Model(Phi3PreTrainedModel):
    """
    Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`Phi3DecoderLayer`]

    Args:
        config: Phi3Config
    """

    def __init__(self, config: Phi3Config):
        super().__init__(config)
        self.padding_idx = config.pad_token_id
        self.vocab_size = config.vocab_size

        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
        self.embed_dropout = nn.Dropout(config.embd_pdrop)
        self.layers = nn.ModuleList(
            [Phi3DecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
        )
        self._attn_implementation = config._attn_implementation
        self.norm = Phi3RMSNorm(config.hidden_size, eps=config.rms_norm_eps)

        self.gradient_checkpointing = False
        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.embed_tokens

    def set_input_embeddings(self, value):
        self.embed_tokens = value

    def forward(
        self,
        input_ids: mindspore.Tensor = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[List[mindspore.Tensor]] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
        cache_position: Optional[mindspore.Tensor] = None,
    ) -> Union[Tuple, BaseModelOutputWithPast]:
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        use_cache = use_cache if use_cache is not None else self.config.use_cache

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if (input_ids is None) ^ (inputs_embeds is not None):
            raise ValueError(
                "You cannot specify both input_ids and inputs_embeds at the same time, and must specify either one"
            )

        if self.gradient_checkpointing and self.training:
            if use_cache:
                logger.warning_once(
                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
                )
                use_cache = False

        use_legacy_cache = False
        if use_cache and not isinstance(past_key_values, Cache) and not self.training:
            use_legacy_cache = True
            past_key_values = DynamicCache.from_legacy_cache(past_key_values)
            logger.warning_once(
                "We detected that you are passing `past_key_values` as a tuple and this is deprecated. "
                "Please use an appropriate `Cache` class"
            )

        if inputs_embeds is None:
            inputs_embeds = self.embed_tokens(input_ids)

        if cache_position is None:
            past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
            cache_position = ops.arange(
                past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1]
            )
        if position_ids is None:
            position_ids = cache_position.unsqueeze(0)

        causal_mask = self._update_causal_mask(
            attention_mask, inputs_embeds, cache_position, past_key_values, output_attentions
        )

        hidden_states = inputs_embeds

        # decoder layers
        all_hidden_states = () if output_hidden_states else None
        all_self_attns = () if output_attentions else None
        next_decoder_cache = None

        for decoder_layer in self.layers:
            if output_hidden_states:
                all_hidden_states += (hidden_states,)

            if self.gradient_checkpointing and self.training:
                layer_outputs = self._gradient_checkpointing_func(
                    decoder_layer.__call__,
                    hidden_states,
                    causal_mask,
                    position_ids,
                    past_key_values,
                    output_attentions,
                    use_cache,
                    cache_position,
                )
            else:
                layer_outputs = decoder_layer(
                    hidden_states,
                    attention_mask=causal_mask,
                    position_ids=position_ids,
                    past_key_value=past_key_values,
                    output_attentions=output_attentions,
                    use_cache=use_cache,
                    cache_position=cache_position,
                )

            hidden_states = layer_outputs[0]

            if use_cache:
                next_decoder_cache = layer_outputs[2 if output_attentions else 1]

            if output_attentions:
                all_self_attns += (layer_outputs[1],)

        hidden_states = self.norm(hidden_states)

        # add hidden states from the last decoder layer
        if output_hidden_states:
            all_hidden_states += (hidden_states,)

        next_cache = None
        if use_cache:
            next_cache = next_decoder_cache.to_legacy_cache() if use_legacy_cache else next_decoder_cache
        if not return_dict:
            return tuple(v for v in [hidden_states, next_cache, all_hidden_states, all_self_attns] if v is not None)
        return BaseModelOutputWithPast(
            last_hidden_state=hidden_states,
            past_key_values=next_cache,
            hidden_states=all_hidden_states,
            attentions=all_self_attns,
        )

    # Copied from transformers.models.llama.modeling_llama.LlamaModel._update_causal_mask
    def _update_causal_mask(
        self,
        attention_mask: mindspore.Tensor,
        input_tensor: mindspore.Tensor,
        cache_position: mindspore.Tensor,
        past_key_values: Cache,
        output_attentions: bool,
    ):

        # For SDPA, when possible, we will rely on its `is_causal` argument instead of its `attn_mask` argument, in
        # order to dispatch on Flash Attention 2. This feature is not compatible with static cache, as SDPA will fail
        # to infer the attention mask.
        past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
        using_static_cache = isinstance(past_key_values, StaticCache)

        dtype = input_tensor.dtype
        min_dtype = float(ops.finfo(dtype).min)
        sequence_length = input_tensor.shape[1]
        if using_static_cache:
            target_length = past_key_values.get_max_length()
        else:
            target_length = (
                attention_mask.shape[-1]
                if isinstance(attention_mask, mindspore.Tensor)
                else past_seen_tokens + sequence_length + 1
            )

        # In case the provided `attention` mask is 2D, we generate a causal mask here (4D).
        causal_mask = _prepare_4d_causal_attention_mask_with_cache_position(
            attention_mask,
            sequence_length=sequence_length,
            target_length=target_length,
            dtype=dtype,
            min_dtype=min_dtype,
            cache_position=cache_position,
            batch_size=input_tensor.shape[0],
        )

        return causal_mask

mindnlp.transformers.models.phi3.modeling_phi3.Phi3RMSNorm

Bases: Module

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

class Phi3RMSNorm(nn.Module):
    def __init__(self, hidden_size, eps=1e-6):
        """
        Phi3RMSNorm is equivalent to T5LayerNorm
        """
        super().__init__()
        self.weight = nn.Parameter(ops.ones(hidden_size))
        self.variance_epsilon = eps

    def forward(self, hidden_states):
        input_dtype = hidden_states.dtype
        hidden_states = hidden_states.to(mindspore.float32)
        variance = ops.mean(hidden_states.pow(2), -1, keepdim=True)
        hidden_states = hidden_states * ops.rsqrt(variance + self.variance_epsilon)
        return self.weight * hidden_states.to(input_dtype)

    def extra_repr(self):
        return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"

mindnlp.transformers.models.phi3.modeling_phi3.Phi3RMSNorm.__init__(hidden_size, eps=1e-06)

Phi3RMSNorm is equivalent to T5LayerNorm

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def __init__(self, hidden_size, eps=1e-6):
    """
    Phi3RMSNorm is equivalent to T5LayerNorm
    """
    super().__init__()
    self.weight = nn.Parameter(ops.ones(hidden_size))
    self.variance_epsilon = eps

mindnlp.transformers.models.phi3.modeling_phi3.apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1)

Applies Rotary Position Embedding to the query and key tensors.

PARAMETER	DESCRIPTION
q	The query tensor. TYPE: `mindspore.Tensor`
k	The key tensor. TYPE: `mindspore.Tensor`
cos	The cosine part of the rotary embedding. TYPE: `mindspore.Tensor`
sin	The sine part of the rotary embedding. TYPE: `mindspore.Tensor`
position_ids	Deprecated and unused. TYPE: `mindspore.Tensor`, *optional* DEFAULT: None
unsqueeze_dim	The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
    """Applies Rotary Position Embedding to the query and key tensors.

    Args:
        q (`mindspore.Tensor`): The query tensor.
        k (`mindspore.Tensor`): The key tensor.
        cos (`mindspore.Tensor`): The cosine part of the rotary embedding.
        sin (`mindspore.Tensor`): The sine part of the rotary embedding.
        position_ids (`mindspore.Tensor`, *optional*):
            Deprecated and unused.
        unsqueeze_dim (`int`, *optional*, defaults to 1):
            The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
            sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
            that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
            k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
            cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
            the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
    Returns:
        `tuple(mindspore.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
    """
    cos = cos.unsqueeze(unsqueeze_dim)
    sin = sin.unsqueeze(unsqueeze_dim)
    q_embed = (q * cos) + (rotate_half(q) * sin)
    k_embed = (k * cos) + (rotate_half(k) * sin)
    return q_embed, k_embed

mindnlp.transformers.models.phi3.modeling_phi3.repeat_kv(hidden_states, n_rep)

This is the equivalent of ops.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def repeat_kv(hidden_states: mindspore.Tensor, n_rep: int) -> mindspore.Tensor:
    """
    This is the equivalent of ops.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
    """
    batch, num_key_value_heads, slen, head_dim = hidden_states.shape
    if n_rep == 1:
        return hidden_states
    hidden_states = hidden_states[:, :, None, :, :].broadcast_to((batch, num_key_value_heads, n_rep, slen, head_dim))
    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim)

mindnlp.transformers.models.phi3.modeling_phi3.rotate_half(x)

Rotates half the hidden dims of the input.

Source code in mindnlp\transformers\models\phi3\modeling_phi3.py

def rotate_half(x):
    """Rotates half the hidden dims of the input."""
    x1 = x[..., : x.shape[-1] // 2]
    x2 = x[..., x.shape[-1] // 2 :]
    return ops.cat((-x2, x1), dim=-1)