feat(modeling_stablelm_epoch.py): add support for AutoModelForSequenceClassification

config.json

@@ -1,10 +1,12 @@
 {
   "architectures": [
-    "StableLMEpochForCausalLM"
+    "StableLMEpochForCausalLM",
+    "StableLMEpochForSequenceClassification"
   ],
   "auto_map": {
     "AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
-    "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
+    "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM",
+    "AutoModelForSequenceClassification": "modeling_stablelm_epoch.StableLMEpochForSequenceClassification"
   },
   "bos_token_id": 100257,
   "eos_token_id": 100257,

modeling_stablelm_epoch.py

@@ -17,7 +17,7 @@
 # https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py
 # https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt_neox/modeling_gpt_neox.py
 """ PyTorch StableLM Epoch model. """
-from typing import Optional, Tuple, Union
+from typing import Optional, Tuple, Union, List
 import math
 import warnings
 
@@ -25,12 +25,13 @@ import torch
 import torch.nn.functional as F
 import torch.utils.checkpoint
 from torch import nn
-from torch.nn import CrossEntropyLoss
+from torch.nn import CrossEntropyLoss, BCEWithLogitsLoss, MSELoss
 
 from transformers.cache_utils import Cache
 from transformers.modeling_outputs import (
     BaseModelOutputWithPast,
     CausalLMOutputWithPast,
+    SequenceClassifierOutputWithPast,
 )
 from transformers.modeling_utils import PreTrainedModel
 from transformers.utils import logging, is_flash_attn_greater_or_equal_2_10
@@ -913,5 +914,111 @@ class StableLMEpochForCausalLM(StableLMEpochPreTrainedModel):
         return reordered_past
 
 
+class StableLMEpochForSequenceClassification(StableLMEpochPreTrainedModel):
+    _keys_to_ignore_on_load_missing = [r"lm_head.weight"]
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.num_labels = config.num_labels
+        self.model = StableLMEpochModel(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: 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,
+    ) -> Union[Tuple, SequenceClassifierOutputWithPast]:
+        r"""
+        labels (`torch.LongTensor` 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
+
+        transformer_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 = transformer_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:
+                sequence_lengths = (torch.ne(input_ids, self.config.pad_token_id).sum(-1) - 1).to(logits.device)
+            else:
+                sequence_lengths = -1
+
+        pooled_logits = logits[torch.arange(batch_size, device=logits.device), sequence_lengths]
+
+        loss = None
+        if labels is not None:
+            labels = labels.to(logits.device)
+            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 == torch.long or labels.dtype == torch.int):
+                    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,) + transformer_outputs[1:]
+            return ((loss,) + output) if loss is not None else output
+
+        return SequenceClassifierOutputWithPast(
+            loss=loss,
+            logits=pooled_logits,
+            past_key_values=transformer_outputs.past_key_values,
+            hidden_states=transformer_outputs.hidden_states,
+            attentions=transformer_outputs.attentions,
+        )
+
 StableLMEpochConfig.register_for_auto_class()
 StableLMEpochForCausalLM.register_for_auto_class("AutoModelForCausalLM")
+StableLMEpochForSequenceClassification.register_for_auto_class("AutoModelForSequenceClassification")