File size: 1,670 Bytes
806292b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
from transformers import PreTrainedModel, MistralConfig, MistralModel
import torch.nn as nn
import torch
from typing import Optional, List

class EurusRewardModel(PreTrainedModel):
    config_class = MistralConfig
    def __init__(self, config):
        super().__init__(config)
        self.model = MistralModel(config)
        self.regression_head = nn.Linear(self.config.hidden_size, 1, bias=False)

    def forward( # args are the same as LlamaForCausalLM
        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,
    ):

        transformer_outputs = self.model(
                                input_ids,
                                attention_mask=attention_mask,
                                position_ids=position_ids,
                                past_key_values=past_key_values,
                                inputs_embeds=inputs_embeds,                               
                            )

        hidden_states = transformer_outputs[0]
        rewards = self.regression_head(hidden_states).squeeze(-1)
        
        ends = attention_mask.cumsum(dim=1).argmax(dim=1).view(-1,1)
        rewards = torch.gather(rewards, 1, ends)
        
        return rewards