gemma.py

from typing import List, Optional, Tuple, Union

import torch
from torch.nn import CrossEntropyLoss
from transformers.cache_utils import Cache
from transformers.modeling_outputs import CausalLMOutputWithPast
from transformers.models.gemma.modeling_gemma import (
    _CONFIG_FOR_DOC,
    GEMMA_INPUTS_DOCSTRING,
)
from transformers.utils import (
    add_start_docstrings_to_model_forward,
    replace_return_docstrings,
)

from liger_kernel.transformers.fused_linear_cross_entropy import (
    LigerFusedLinearCrossEntropyLoss,
)


@add_start_docstrings_to_model_forward(GEMMA_INPUTS_DOCSTRING)
@replace_return_docstrings(
    output_type=CausalLMOutputWithPast, config_class=_CONFIG_FOR_DOC
)
def lce_forward(
    self,
    input_ids: torch.LongTensor = None,
    attention_mask: Optional[torch.Tensor] = None,
    position_ids: Optional[torch.LongTensor] = None,
    past_key_values: Optional[Union[Cache, 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,
) -> Union[Tuple, CausalLMOutputWithPast]:
    r"""

    copy paste transformers.models.gemma.modeling_gemma causalLM with loss replaced with liger fused cross entropy

    Args:
        labels (`torch.LongTensor` 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, GemmaForCausalLM

    >>> model = GemmaForCausalLM.from_pretrained("google/gemma-7b")
    >>> tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")

    >>> prompt = "What is your favorite condiment?"
    >>> inputs = tokenizer(prompt, return_tensors="pt")

    >>> # 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]
    "What is your favorite condiment?"
    ```"""
    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,
    )

    hidden_states = outputs[0]

    loss = None
    logits = None

    if self.training and (labels is not None):
        shift_hidden_states = hidden_states[..., :-1, :].contiguous()
        shift_labels = labels[..., 1:].contiguous()

        # flatten

        shift_hidden_states = shift_hidden_states.view(-1, self.config.hidden_size)
        shift_labels = shift_labels.view(-1)

        lce = LigerFusedLinearCrossEntropyLoss()
        loss = lce(self.lm_head.weight, shift_hidden_states, shift_labels)

    else:
        logits = self.lm_head(hidden_states)
        if labels is not None:
            # Upcast to float if we need to compute the loss to avoid potential precision issues
            logits = logits.float()
            # Shift so that tokens < n predict n
            shift_logits = logits[..., :-1, :].contiguous()
            shift_labels = labels[..., 1:].contiguous()
            # Flatten the tokens
            shift_logits = shift_logits.view(-1, self.config.vocab_size)
            shift_labels = shift_labels.view(-1)
            # Ensure tensors are on the same device
            shift_labels = shift_labels.to(shift_logits.device)
            loss_fct = CrossEntropyLoss()
            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,
    )