initial commit

configuration_nucleus.py

@@ -1,89 +0,0 @@
-# This config is based on LLaMA.
-""" Nucleus model configuration"""
-
-from transformers import PretrainedConfig
-from transformers.utils import logging
-
-
-logger = logging.get_logger(__name__)
-
-NUCLEUS_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
-
-
-class NucleusConfig(PretrainedConfig):
-    model_type = "nulceus"
-    keys_to_ignore_at_inference = ["past_key_values"]
-
-    def __init__(
-        self,
-        vocab_size=32000,
-        hidden_size=6656,
-        intermediate_size=17920,
-        num_hidden_layers=40,
-        num_attention_heads=52,
-        num_key_value_heads=52,
-        hidden_act="silu",
-        max_position_embeddings=2048,
-        initializer_range=0.02,
-        rms_norm_eps=1e-6,
-        use_cache=True,
-        pad_token_id=0,
-        bos_token_id=1,
-        eos_token_id=2,
-        pretraining_tp=1,
-        tie_word_embeddings=False,
-        rope_theta=10000.0,
-        rope_scaling=None,
-        attention_bias=False,
-        **kwargs,
-    ):
-        self.vocab_size = vocab_size
-        self.max_position_embeddings = max_position_embeddings
-        self.hidden_size = hidden_size
-        self.intermediate_size = intermediate_size
-        self.num_hidden_layers = num_hidden_layers
-        self.num_attention_heads = num_attention_heads
-
-        # for backward compatibility
-        if num_key_value_heads is None:
-            num_key_value_heads = num_attention_heads
-
-        self.num_key_value_heads = num_key_value_heads
-        self.hidden_act = hidden_act
-        self.initializer_range = initializer_range
-        self.rms_norm_eps = rms_norm_eps
-        self.pretraining_tp = pretraining_tp
-        self.use_cache = use_cache
-        self.rope_theta = rope_theta
-        self.rope_scaling = rope_scaling
-        self._rope_scaling_validation()
-        self.attention_bias = attention_bias
-
-        super().__init__(
-            pad_token_id=pad_token_id,
-            bos_token_id=bos_token_id,
-            eos_token_id=eos_token_id,
-            tie_word_embeddings=tie_word_embeddings,
-            **kwargs,
-        )
-
-    def _rope_scaling_validation(self):
-        """
-        Validate the `rope_scaling` configuration.
-        """
-        if self.rope_scaling is None:
-            return
-
-        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
-            raise ValueError(
-                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
-                f"got {self.rope_scaling}"
-            )
-        rope_scaling_type = self.rope_scaling.get("type", None)
-        rope_scaling_factor = self.rope_scaling.get("factor", None)
-        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
-            raise ValueError(
-                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
-            )
-        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
-            raise ValueError(f"`rope_scaling`'s factor field must be an float > 1, got {rope_scaling_factor}")

modeling_nucleus.py

@@ -1,155 +0,0 @@
-# This code is based on LLaMA
-""" PyTorch Nucleus model."""
-from typing import List, Optional, Tuple, Union
-
-import torch
-import torch.nn.functional as F
-import torch.utils.checkpoint
-from torch import nn
-from torch.nn import CrossEntropyLoss
-
-from transformers.modeling_outputs import CausalLMOutputWithPast
-from .configuration_nucleus import NucleusConfig
-
-from transformers import (
-    LlamaPreTrainedModel,
-    LlamaModel
-)
-
-
-class NucleusForCausalLM(LlamaPreTrainedModel):
-    _tied_weights_keys = ["lm_head.weight"]
-
-    def __init__(self, config: NucleusConfig):
-        super().__init__(config)
-        self.model = LlamaModel(config)
-        self.vocab_size = config.vocab_size
-        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, 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 get_output_embeddings(self):
-        return self.lm_head
-
-    def set_output_embeddings(self, new_embeddings):
-        self.lm_head = new_embeddings
-
-    def set_decoder(self, decoder):
-        self.model = decoder
-
-    def get_decoder(self):
-        return self.model
-
-    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, 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
-
-        # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
-        outputs = self.model(
-            input_ids=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 = outputs[0]
-        if self.config.pretraining_tp > 1:
-            lm_head_slices = self.lm_head.weight.split(self.vocab_size // self.config.pretraining_tp, dim=0)
-            logits = [F.linear(hidden_states, lm_head_slices[i]) for i in range(self.config.pretraining_tp)]
-            logits = torch.cat(logits, dim=-1)
-        else:
-            logits = self.lm_head(hidden_states)
-        logits = logits.float()
-
-        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 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:]
-
-        position_ids = kwargs.get("position_ids", None)
-        if attention_mask is not None and position_ids is None:
-            # create position_ids on the fly for batch generation
-            position_ids = attention_mask.long().cumsum(-1) - 1
-            position_ids.masked_fill_(attention_mask == 0, 1)
-            if past_key_values:
-                position_ids = position_ids[:, -1].unsqueeze(-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(
-            {
-                "position_ids": position_ids,
-                "past_key_values": past_key_values,
-                "use_cache": kwargs.get("use_cache"),
-                "attention_mask": attention_mask,
-            }
-        )
-        return model_inputs
-
-    @staticmethod
-    def _reorder_cache(past_key_values, beam_idx):
-        reordered_past = ()
-        for layer_past in past_key_values:
-            reordered_past += (
-                tuple(past_state.index_select(0, beam_idx.to(past_state.device)) for past_state in layer_past),
-            )
-        return reordered_past
-