optimum/habana/transformers/models/decilm/modeling_decilm.py

"""
Adapted from the following sources:
https://huggingface.co/Deci/DeciLM-7B/blob/main/modeling_decilm.py
"""

from typing import List, Optional, Tuple, Union

import torch
import torch.nn.functional as F
import torch.utils.checkpoint
from torch import nn
from torch.nn import CrossEntropyLoss
from transformers.cache_utils import Cache
from transformers.modeling_outputs import CausalLMOutputWithPast
from transformers.models.auto.modeling_auto import MODEL_FOR_CAUSAL_LM_MAPPING_NAMES
from transformers.models.llama.modeling_llama import (
    LLAMA_INPUTS_DOCSTRING,
    LLAMA_START_DOCSTRING,
    BaseModelOutputWithPast,
    LlamaAttention,
    LlamaDecoderLayer,
    LlamaForCausalLM,
    LlamaMLP,
    LlamaModel,
    LlamaPreTrainedModel,
    LlamaRMSNorm,
    apply_rotary_pos_emb,
    repeat_kv,
)
from transformers.utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging

from ...modeling_attn_mask_utils import _gaudi_prepare_4d_causal_attention_mask
from ..llama.modeling_llama import GaudiLlamaRotaryEmbedding
from .configuration_decilm import DeciLMConfig


MODEL_FOR_CAUSAL_LM_MAPPING_NAMES["deci"] = "DeciLMForCausalLM"
_CONFIG_FOR_DOC = "DeciLMConfig"
logger = logging.get_logger(__name__)


class DeciLMAttention(LlamaAttention):
    """Multi-headed attention from 'Attention Is All You Need' paper"""

    def __init__(self, config: DeciLMConfig, layer_idx: int):
        nn.Module.__init__(self)
        self.config = config
        self.hidden_size = config.hidden_size
        self.num_heads = config.num_attention_heads
        self.head_dim = self.hidden_size // self.num_heads
        self.layer_idx = layer_idx
        self.num_key_value_heads = config.num_key_value_heads_per_layer[layer_idx]
        self.num_key_value_groups = self.num_heads // self.num_key_value_heads
        self.pretraining_tp = config.pretraining_tp
        self.max_position_embeddings = config.max_position_embeddings
        self.rope_theta = getattr(config, "rope_theta", None)

        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})."
            )
        self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
        self.k_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
        self.v_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
        self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False)

        self.rotary_emb = GaudiLlamaRotaryEmbedding(config=self.config)

    def forward(
        self,
        hidden_states: torch.Tensor,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_value: Optional[Tuple[torch.Tensor]] = None,
        output_attentions: bool = False,
        use_cache: bool = False,
        token_idx: Optional[torch.Tensor] = None,
        **kwargs,
    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
        """
        Copied from DeciLMAttention.forward: https://huggingface.co/Deci/DeciLM-7B/blob/main/modeling_decilm.py
        The only differences are:
        - add new args token_idx
        """
        bsz, q_len, _ = hidden_states.size()
        is_decode = past_key_value is not None
        if self.pretraining_tp > 1:
            key_value_slicing = (self.num_key_value_heads * self.head_dim) // self.pretraining_tp
            query_slices = self.q_proj.weight.split((self.num_heads * self.head_dim) // self.pretraining_tp, dim=0)
            key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
            value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)

            query_states = [F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)]
            query_states = torch.cat(query_states, dim=-1)

            key_states = [F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)]
            key_states = torch.cat(key_states, dim=-1)

            value_states = [F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)]
            value_states = torch.cat(value_states, dim=-1)

        else:
            query_states = self.q_proj(hidden_states)
            key_states = self.k_proj(hidden_states)
            value_states = self.v_proj(hidden_states)

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

        kv_seq_len = key_states.shape[-2]
        if past_key_value is not None:
            if token_idx is None:
                kv_seq_len += past_key_value[0].shape[-2]
            else:
                kv_seq_len = past_key_value[0].shape[-2]
        cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)

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

        if past_key_value is not None:
            # reuse k, v, self_attention
            if token_idx is None:
                key_states = torch.cat([past_key_value[0], key_states], dim=2)
                value_states = torch.cat([past_key_value[1], value_states], dim=2)
            else:
                past_key_value[0].index_add_(
                    2, token_idx - 1, key_states - torch.index_select(past_key_value[0], 2, token_idx - 1)
                )
                past_key_value[1].index_add_(
                    2, token_idx - 1, value_states - torch.index_select(past_key_value[1], 2, token_idx - 1)
                )
                key_states = past_key_value[0]
                value_states = past_key_value[1]

        past_key_value = (key_states, value_states) if use_cache else None

        # 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)
        if is_decode:
            attn_output = F.scaled_dot_product_attention(
                query_states, key_states, value_states, is_causal=False, attn_mask=attention_mask
            )
            attn_output = attn_output.contiguous().view(bsz, q_len, self.hidden_size)
        else:
            attn_output = F.scaled_dot_product_attention(
                query_states, key_states, value_states, is_causal=attention_mask is None, attn_mask=attention_mask
            )

            if attn_output.size() != (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.size()}"
                )

            attn_output = attn_output.transpose(1, 2).contiguous().view(bsz, q_len, self.hidden_size)

        if self.pretraining_tp > 1:
            attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
            o_proj_slices = self.o_proj.weight.split(self.hidden_size // self.pretraining_tp, dim=1)
            attn_output = sum([F.linear(attn_output[i], o_proj_slices[i]) for i in range(self.pretraining_tp)])
        else:
            attn_output = self.o_proj(attn_output)

        attn_weights = None

        return attn_output, attn_weights, past_key_value


class DeciLMDecoderLayer(LlamaDecoderLayer):
    def __init__(self, config: DeciLMConfig, layer_idx: int):
        nn.Module.__init__(self)
        self.hidden_size = config.hidden_size
        self.layer_idx = layer_idx
        self.self_attn = DeciLMAttention(config=config, layer_idx=layer_idx)
        self.mlp = LlamaMLP(config)
        self.input_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
        self.post_attention_layernorm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)

    def forward(
        self,
        hidden_states: torch.Tensor,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_value: Optional[Cache] = None,
        output_attentions: Optional[bool] = False,
        use_cache: Optional[bool] = False,
        cache_position: Optional[torch.LongTensor] = None,
        position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
        token_idx: Optional[torch.Tensor] = None,
        **kwargs,
    ) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]]:
        residual = hidden_states

        hidden_states = self.input_layernorm(hidden_states)

        # Self Attention
        hidden_states, 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,
            position_embeddings=position_embeddings,
            token_idx=token_idx,
            **kwargs,
        )
        hidden_states = residual + hidden_states

        # Fully Connected
        residual = hidden_states
        hidden_states = self.post_attention_layernorm(hidden_states)
        hidden_states = self.mlp(hidden_states)
        hidden_states = residual + hidden_states

        outputs = (hidden_states,)

        if output_attentions:
            outputs += (self_attn_weights,)

        if use_cache:
            outputs += (present_key_value,)

        return outputs


@add_start_docstrings(
    "The bare DeciLM Model outputting raw hidden-states without any specific head on top.",
    LLAMA_START_DOCSTRING,
)
class DeciLMPreTrainedModel(LlamaPreTrainedModel):
    config_class = DeciLMConfig
    _no_split_modules = ["DeciLMDecoderLayer"]
    _keys_to_ignore_on_load_missing = ["self_attn.rotary_emb.inv_freq"]


@add_start_docstrings(
    "The bare DeciLM Model outputting raw hidden-states without any specific head on top.",
    LLAMA_START_DOCSTRING,
)
class DeciLMModel(LlamaModel, DeciLMPreTrainedModel):
    """
    Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`DeciLMDecoderLayer`]

    Args:
        config: DeciLMConfig
    """

    def __init__(self, config: DeciLMConfig):
        DeciLMPreTrainedModel.__init__(self, 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.layers = nn.ModuleList(
            [DeciLMDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
        )
        self.norm = LlamaRMSNorm(config.hidden_size, eps=config.rms_norm_eps)

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

    @add_start_docstrings_to_model_forward(LLAMA_INPUTS_DOCSTRING)
    def forward(
        self,
        input_ids: torch.LongTensor = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[List[torch.FloatTensor]] = None,
        inputs_embeds: Optional[torch.FloatTensor] = 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[torch.LongTensor] = None,
        token_idx: Optional[torch.Tensor] = None,
    ) -> Union[Tuple, BaseModelOutputWithPast]:
        """
        Copied from DeciLMModel.forward: https://huggingface.co/Deci/DeciLM-7B/blob/main/modeling_decilm.py
        The only differences are:
        - add new args token_idx
        """
        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

        # retrieve input_ids and inputs_embeds
        if input_ids is not None and inputs_embeds is not None:
            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
        elif input_ids is not None:
            batch_size, seq_length = input_ids.shape[:2]
        elif inputs_embeds is not None:
            batch_size, seq_length = inputs_embeds.shape[:2]
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        past_key_values_length = 0
        if past_key_values is not None:
            past_key_values_length = past_key_values[0][0].shape[2]

        if position_ids is None:
            device = input_ids.device if input_ids is not None else inputs_embeds.device
            position_ids = torch.arange(
                past_key_values_length, seq_length + past_key_values_length, dtype=torch.long, device=device
            )
            position_ids = position_ids.unsqueeze(0)

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

        attention_mask = attention_mask if (attention_mask is not None and 0 in attention_mask) else None
        if attention_mask is not None:
            # 4d mask is passed through the layers
            attention_mask = _gaudi_prepare_4d_causal_attention_mask(
                attention_mask, (batch_size, seq_length), inputs_embeds, past_key_values_length
            )

        # embed positions
        hidden_states = inputs_embeds

        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

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

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

            past_key_value = past_key_values[idx] if past_key_values is not None else None

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

            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 = next_decoder_cache if use_cache else None
        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,
        )


class DeciLMForCausalLM(LlamaForCausalLM, DeciLMPreTrainedModel):
    def __init__(self, config):
        DeciLMPreTrainedModel.__init__(self, config)
        self.model = DeciLMModel(config)
        self.pretraining_tp = config.pretraining_tp
        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()

    def prepare_inputs_for_generation(
        self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, cache_position=None, **kwargs
    ):
        """
        Copied from LlamaForCausalLM.prepare_inputs_for_generation: https://github.com/huggingface/transformers/blob/v4.40.2/src/transformers/models/llama/modeling_llama.py#L1258
        The only differences are:
        - add token_idx support
        """
        token_idx = kwargs.get("token_idx")
        # With static cache, the `past_key_values` is None
        # TODO joao: standardize interface for the different Cache classes and remove of this if
        has_static_cache = False
        if past_key_values is None:
            past_key_values = getattr(getattr(self.model.layers[0], "self_attn", {}), "past_key_value", None)
            has_static_cache = past_key_values is not None

        past_length = 0
        if past_key_values is not None:
            if token_idx is not None:
                idx = token_idx + kwargs.get("inputs_embeds_offset", 0) - 1
                input_ids = torch.index_select(input_ids, 1, idx)
            else:
                if isinstance(past_key_values, Cache):
                    past_length = cache_position[0] if cache_position is not None else past_key_values.get_seq_length()
                    max_cache_length = (
                        torch.tensor(past_key_values.get_max_length(), device=input_ids.device)
                        if past_key_values.get_max_length() is not None
                        else None
                    )
                    cache_length = (
                        past_length if max_cache_length is None else torch.min(max_cache_length, past_length)
                    )
                # TODO joao: remove this `else` after `generate` prioritizes `Cache` objects
                else:
                    cache_length = past_length = past_key_values[0][0].shape[2]
                    max_cache_length = None

                # Keep only the unprocessed tokens:
                # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
                # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
                # input)
                if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                    input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]
                # 2 - If the past_length is smaller than input_ids', then input_ids holds all input tokens. We can discard
                # input_ids based on the past_length.
                elif past_length < input_ids.shape[1]:
                    input_ids = input_ids[:, past_length:]
                # 3 - Otherwise (past_length >= input_ids.shape[1]), let's assume input_ids only has unprocessed tokens.

                # If we are about to go beyond the maximum cache length, we need to crop the input attention mask.
                if (
                    max_cache_length is not None
                    and attention_mask is not None
                    and cache_length + input_ids.shape[1] > max_cache_length
                ):
                    attention_mask = attention_mask[:, -max_cache_length:]

        position_ids = kwargs.get("position_ids", None)
        if attention_mask is not None and position_ids is None:
            # create position_ids on the fly for batch generation
            position_ids = attention_mask.long().cumsum(-1) - 1
            position_ids.masked_fill_(attention_mask == 0, 1)
            if past_key_values:
                if token_idx is not None:
                    position_ids = torch.index_select(position_ids, 1, token_idx - 1)
                else:
                    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 past_key_values is None:
            model_inputs = {"inputs_embeds": inputs_embeds}
        else:
            # The `contiguous()` here is necessary to have a static stride during decoding. torchdynamo otherwise
            # recompiles graphs as the stride of the inputs is a guard. Ref: https://github.com/huggingface/transformers/pull/29114
            # TODO: use `next_tokens` directly instead.
            model_inputs = {"input_ids": input_ids.contiguous()}

        input_length = position_ids.shape[-1] if position_ids is not None else input_ids.shape[-1]
        if cache_position is None:
            cache_position = torch.arange(past_length, past_length + input_length, device=input_ids.device)
        else:
            cache_position = cache_position[-input_length:]

        if has_static_cache:
            past_key_values = None

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

    def forward(
        self,
        input_ids: torch.LongTensor = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[List[torch.FloatTensor]] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        labels: Optional[torch.LongTensor] = 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[torch.LongTensor] = None,
        token_idx: Optional[torch.Tensor] = None,
    ) -> Union[Tuple, CausalLMOutputWithPast]:
        """
        Copied from LlamaForCausalLM.forward: https://github.com/huggingface/transformers/blob/v4.40.2/src/transformers/models/llama/modeling_llama.py#L1165
        The only differences are:
        - add token_idx support
        """
        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,
            cache_position=cache_position,
            token_idx=token_idx,
        )

        hidden_states = outputs[0]
        if self.config.pretraining_tp > 1:
            lm_head_slices = self.lm_head.weight.split(self.vocab_size // self.config.pretraining_tp, dim=0)
            logits = [F.linear(hidden_states, lm_head_slices[i]) for i in range(self.config.pretraining_tp)]
            logits = torch.cat(logits, dim=-1)
        else:
            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, :].contiguous()
            shift_labels = labels[..., 1:].contiguous()
            # 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
            shift_labels = shift_labels.to(shift_logits.device)
            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,
        )