Spaces:
Sleeping
Sleeping
| import os | |
| from typing import List, Optional, Tuple, Union | |
| import torch | |
| import torch.nn as nn | |
| from torch.nn import CrossEntropyLoss | |
| from transformers import AutoConfig, AutoModelForCausalLM, \ | |
| PhiModel, PhiPreTrainedModel | |
| from transformers.modeling_outputs import CausalLMOutputWithPast | |
| from ..llava_arch import LlavaMetaModel, LlavaMetaForCausalLM | |
| from transformers.utils import logging | |
| from .configuration_llava_phi import LlavaPhiConfig | |
| logger = logging.get_logger(__name__) | |
| class LLavaPhiModel(LlavaMetaModel, PhiModel): | |
| config_class = LlavaPhiConfig | |
| def __init__(self, config): | |
| super(LLavaPhiModel, self).__init__(config) | |
| class LlavaPhiForCausalLM(PhiPreTrainedModel, LlavaMetaForCausalLM): | |
| config_class = LlavaPhiConfig | |
| def __init__(self, config): | |
| super(PhiPreTrainedModel, self).__init__(config) | |
| self.model = LLavaPhiModel(config) | |
| self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=True) | |
| # Initialize weights and apply final processing | |
| self.post_init() | |
| def get_model(self): | |
| return self.model | |
| def forward( | |
| self, | |
| input_ids: torch.LongTensor = None, | |
| attention_mask: Optional[torch.Tensor] = 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, | |
| images: Optional[torch.FloatTensor] = None, | |
| return_dict: Optional[bool] = None, | |
| ) -> Union[Tuple, CausalLMOutputWithPast]: | |
| 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 | |
| input_ids, attention_mask, past_key_values, inputs_embeds, labels = self.prepare_inputs_labels_for_multimodal( | |
| input_ids, attention_mask, past_key_values, labels, images) | |
| # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn) | |
| outputs = self.model( | |
| input_ids=input_ids, | |
| attention_mask=attention_mask, | |
| 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) | |
| 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/pipeline 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, | |
| ) | |
| def prepare_inputs_for_generation( | |
| self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs | |
| ): | |
| if past_key_values: | |
| input_ids = input_ids[:, -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: | |
| model_inputs = {"input_ids": input_ids} | |
| model_inputs.update( | |
| { | |
| "past_key_values": past_key_values, | |
| "use_cache": kwargs.get("use_cache"), | |
| "attention_mask": attention_mask, | |
| "images": kwargs.get("images", None), | |
| } | |
| ) | |
| return model_inputs | |
| AutoConfig.register("llava_phi", LlavaPhiConfig) | |
| AutoModelForCausalLM.register(LlavaPhiConfig, LlavaPhiForCausalLM) | |