LLM-foundry update June 27, 2023 21:25:19 (#4)

- LLM-foundry update June 27, 2023 21:25:19 (2443a6bcb624ea3dec72a71af64c98fb68d0e359)


Co-authored-by: Dan Biderman <danbider@users.noreply.huggingface.co>

modeling_mpt.py

@@ -140,7 +140,7 @@ class MPTModel(MPTPreTrainedModel):
         attn_bias = attn_bias.masked_fill(cannot_attend, min_val)
         return attn_bias
 
-    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None):
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.Tensor]=None):
         return_dict = return_dict if return_dict is not None else self.config.return_dict
         use_cache = use_cache if use_cache is not None else self.config.use_cache
         if attention_mask is not None:
@@ -156,6 +156,8 @@ class MPTModel(MPTPreTrainedModel):
             raise NotImplementedError('MPT does not support training with left padding.')
         if self.prefix_lm and prefix_mask is None:
             raise ValueError('prefix_mask is a required argument when MPT is configured with prefix_lm=True.')
+        if inputs_embeds is not None:
+            raise NotImplementedError('inputs_embeds is not implemented for MPT.')
         if self.training:
             if self.attn_uses_sequence_id and sequence_id is None:
                 raise ValueError('sequence_id is a required argument when MPT is configured with attn_uses_sequence_id=True ' + 'and the model is in train mode.')
@@ -225,6 +227,7 @@ class MPTForCausalLM(MPTPreTrainedModel):
         super().__init__(config)
         if not config.tie_word_embeddings:
             raise ValueError('MPTForCausalLM only supports tied word embeddings')
+        print(f'Instantiating an MPTForCausalLM model from {__file__}')
         self.transformer = MPTModel(config)
         for child in self.transformer.children():
             if isinstance(child, torch.nn.ModuleList):
@@ -259,9 +262,11 @@ class MPTForCausalLM(MPTPreTrainedModel):
     def get_decoder(self):
         return self.transformer
 
-    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, labels: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None):
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, labels: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.FloatTensor]=None):
         return_dict = return_dict if return_dict is not None else self.config.return_dict
         use_cache = use_cache if use_cache is not None else self.config.use_cache
+        if inputs_embeds is not None:
+            raise NotImplementedError('inputs_embeds has to be None (for hf/peft support).')
         outputs = self.transformer(input_ids=input_ids, past_key_values=past_key_values, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id, return_dict=return_dict, output_attentions=output_attentions, output_hidden_states=output_hidden_states, use_cache=use_cache)
         logits = self.transformer.wte(outputs.last_hidden_state.to(self.transformer.wte.weight.device), True)
         if self.logit_scale is not None:

norm.py

@@ -25,7 +25,7 @@ class LPLayerNorm(torch.nn.LayerNorm):
             return torch.nn.functional.layer_norm(downcast_x, self.normalized_shape, downcast_weight, downcast_bias, self.eps)
 
 def rms_norm(x, weight=None, eps=1e-05):
-    output = x / torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + eps)
+    output = x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + eps)
     if weight is not None:
         return output * weight
     return output