optimum/graphcore/models/mt5/modeling_mt5.py [72:173]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - def forward( self, hidden_states, attention_mask=None, position_bias=None, encoder_hidden_states=None, encoder_attention_mask=None, encoder_decoder_position_bias=None, layer_head_mask=None, cross_attn_layer_head_mask=None, past_key_value=None, use_cache=False, output_attentions=False, return_dict=True, ): if past_key_value is not None: if not self.is_decoder: logger.warning("`past_key_values` is passed to the encoder. Please make sure this is intended.") expected_num_past_key_values = 2 if encoder_hidden_states is None else 4 if len(past_key_value) != expected_num_past_key_values: raise ValueError( f"There should be {expected_num_past_key_values} past states. " f"{'2 (past / key) for cross attention. ' if expected_num_past_key_values == 4 else ''}" f"Got {len(past_key_value)} past key / value states" ) self_attn_past_key_value = past_key_value[:2] cross_attn_past_key_value = past_key_value[2:] else: self_attn_past_key_value, cross_attn_past_key_value = None, None self_attention_outputs = self.layer[0]( hidden_states, attention_mask=attention_mask, position_bias=position_bias, layer_head_mask=layer_head_mask, past_key_value=self_attn_past_key_value, use_cache=use_cache, output_attentions=output_attentions, ) hidden_states, present_key_value_state = self_attention_outputs[:2] attention_outputs = self_attention_outputs[2:] # Keep self-attention outputs and relative position weights # clamp inf values to enable fp16 training # Custom: Remove check for inf if hidden_states.dtype == torch.float16: clamp_value = torch.tensor(torch.finfo(hidden_states.dtype).max - 1000, dtype=hidden_states.dtype) hidden_states = torch.clamp(hidden_states, min=-clamp_value, max=clamp_value) do_cross_attention = self.is_decoder and encoder_hidden_states is not None if do_cross_attention: # the actual query length is unknown for cross attention # if using past key value states. Need to inject it here if present_key_value_state is not None: query_length = present_key_value_state[0].shape[2] else: query_length = None cross_attention_outputs = self.layer[1]( hidden_states, key_value_states=encoder_hidden_states, attention_mask=encoder_attention_mask, position_bias=encoder_decoder_position_bias, layer_head_mask=cross_attn_layer_head_mask, past_key_value=cross_attn_past_key_value, query_length=query_length, use_cache=use_cache, output_attentions=output_attentions, ) hidden_states = cross_attention_outputs[0] # clamp inf values to enable fp16 training # Custom: Remove check for inf if hidden_states.dtype == torch.float16: clamp_value = torch.tensor(torch.finfo(hidden_states.dtype).max - 1000, dtype=hidden_states.dtype) hidden_states = torch.clamp(hidden_states, min=-clamp_value, max=clamp_value) # Combine self attn and cross attn key value states if present_key_value_state is not None: present_key_value_state = present_key_value_state + cross_attention_outputs[1] # Keep cross-attention outputs and relative position weights attention_outputs = attention_outputs + cross_attention_outputs[2:] # Apply Feed Forward layer hidden_states = self.layer[-1](hidden_states) # clamp inf values to enable fp16 training # Custom: Remove check for inf if hidden_states.dtype == torch.float16: clamp_value = torch.tensor(torch.finfo(hidden_states.dtype).max - 1000, dtype=hidden_states.dtype) hidden_states = torch.clamp(hidden_states, min=-clamp_value, max=clamp_value) outputs = (hidden_states,) if use_cache: outputs = outputs + (present_key_value_state,) + attention_outputs else: outputs = outputs + attention_outputs return outputs # hidden-states, present_key_value_states, (self-attention position bias), (self-attention weights), (cross-attention position bias), (cross-attention weights) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - optimum/graphcore/models/t5/modeling_t5.py [201:302]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - def forward( self, hidden_states, attention_mask=None, position_bias=None, encoder_hidden_states=None, encoder_attention_mask=None, encoder_decoder_position_bias=None, layer_head_mask=None, cross_attn_layer_head_mask=None, past_key_value=None, use_cache=False, output_attentions=False, return_dict=True, ): if past_key_value is not None: if not self.is_decoder: logger.warning("`past_key_values` is passed to the encoder. Please make sure this is intended.") expected_num_past_key_values = 2 if encoder_hidden_states is None else 4 if len(past_key_value) != expected_num_past_key_values: raise ValueError( f"There should be {expected_num_past_key_values} past states. " f"{'2 (past / key) for cross attention. ' if expected_num_past_key_values == 4 else ''}" f"Got {len(past_key_value)} past key / value states" ) self_attn_past_key_value = past_key_value[:2] cross_attn_past_key_value = past_key_value[2:] else: self_attn_past_key_value, cross_attn_past_key_value = None, None self_attention_outputs = self.layer[0]( hidden_states, attention_mask=attention_mask, position_bias=position_bias, layer_head_mask=layer_head_mask, past_key_value=self_attn_past_key_value, use_cache=use_cache, output_attentions=output_attentions, ) hidden_states, present_key_value_state = self_attention_outputs[:2] attention_outputs = self_attention_outputs[2:] # Keep self-attention outputs and relative position weights # clamp inf values to enable fp16 training # Custom: Remove check for inf if hidden_states.dtype == torch.float16: clamp_value = torch.tensor(torch.finfo(hidden_states.dtype).max - 1000, dtype=hidden_states.dtype) hidden_states = torch.clamp(hidden_states, min=-clamp_value, max=clamp_value) do_cross_attention = self.is_decoder and encoder_hidden_states is not None if do_cross_attention: # the actual query length is unknown for cross attention # if using past key value states. Need to inject it here if present_key_value_state is not None: query_length = present_key_value_state[0].shape[2] else: query_length = None cross_attention_outputs = self.layer[1]( hidden_states, key_value_states=encoder_hidden_states, attention_mask=encoder_attention_mask, position_bias=encoder_decoder_position_bias, layer_head_mask=cross_attn_layer_head_mask, past_key_value=cross_attn_past_key_value, query_length=query_length, use_cache=use_cache, output_attentions=output_attentions, ) hidden_states = cross_attention_outputs[0] # clamp inf values to enable fp16 training # Custom: Remove check for inf if hidden_states.dtype == torch.float16: clamp_value = torch.tensor(torch.finfo(hidden_states.dtype).max - 1000, dtype=hidden_states.dtype) hidden_states = torch.clamp(hidden_states, min=-clamp_value, max=clamp_value) # Combine self attn and cross attn key value states if present_key_value_state is not None: present_key_value_state = present_key_value_state + cross_attention_outputs[1] # Keep cross-attention outputs and relative position weights attention_outputs = attention_outputs + cross_attention_outputs[2:] # Apply Feed Forward layer hidden_states = self.layer[-1](hidden_states) # clamp inf values to enable fp16 training # Custom: Remove check for inf if hidden_states.dtype == torch.float16: clamp_value = torch.tensor(torch.finfo(hidden_states.dtype).max - 1000, dtype=hidden_states.dtype) hidden_states = torch.clamp(hidden_states, min=-clamp_value, max=clamp_value) outputs = (hidden_states,) if use_cache: outputs = outputs + (present_key_value_state,) + attention_outputs else: outputs = outputs + attention_outputs return outputs # hidden-states, present_key_value_states, (self-attention position bias), (self-attention weights), (cross-attention position bias), (cross-attention weights) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -