keep internlm2 only

configuration_internlm.py

@@ -1,164 +0,0 @@
-# coding=utf-8
-# Copyright (c) InternLM. All rights reserved.
-#
-# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
-# and OPT implementations in this library. It has been modified from its
-# original forms to accommodate minor architectural differences compared
-# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-""" InternLM model configuration"""
-
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import logging
-
-logger = logging.get_logger(__name__)
-
-INTERNLM_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
-
-
-class InternLMConfig(PretrainedConfig):
-    r"""
-    This is the configuration class to store the configuration of a [`InternLMModel`]. It is used to instantiate
-    an InternLM model according to the specified arguments, defining the model architecture. Instantiating a
-    configuration with the defaults will yield a similar configuration to that of the InternLM-7B.
-
-    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
-    documentation from [`PretrainedConfig`] for more information.
-
-
-    Args:
-        vocab_size (`int`, *optional*, defaults to 32000):
-            Vocabulary size of the InternLM model. Defines the number of different tokens that can be represented by the
-            `inputs_ids` passed when calling [`InternLMModel`]
-        hidden_size (`int`, *optional*, defaults to 4096):
-            Dimension of the hidden representations.
-        intermediate_size (`int`, *optional*, defaults to 11008):
-            Dimension of the MLP representations.
-        num_hidden_layers (`int`, *optional*, defaults to 32):
-            Number of hidden layers in the Transformer encoder.
-        num_attention_heads (`int`, *optional*, defaults to 32):
-            Number of attention heads for each attention layer in the Transformer encoder.
-        num_key_value_heads (`int`, *optional*):
-            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
-            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
-            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
-            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
-            by meanpooling all the original heads within that group. For more details checkout [this
-            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
-            `num_attention_heads`.
-        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
-            The non-linear activation function (function or string) in the decoder.
-        max_position_embeddings (`int`, *optional*, defaults to 2048):
-            The maximum sequence length that this model might ever be used with. Typically set this to something large
-            just in case (e.g., 512 or 1024 or 2048).
-        initializer_range (`float`, *optional*, defaults to 0.02):
-            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
-        rms_norm_eps (`float`, *optional*, defaults to 1e-12):
-            The epsilon used by the rms normalization layers.
-        use_cache (`bool`, *optional*, defaults to `True`):
-            Whether or not the model should return the last key/values attentions (not used by all models). Only
-            relevant if `config.is_decoder=True`.
-        tie_word_embeddings(`bool`, *optional*, defaults to `False`):
-            Whether to tie weight embeddings
-        Example:
-
-    ```python
-    >>> from transformers import InternLMModel, InternLMConfig
-
-    >>> # Initializing a InternLM internlm-7b style configuration
-    >>> configuration = InternLMConfig()
-
-    >>> # Initializing a model from the internlm-7b style configuration
-    >>> model = InternLMModel(configuration)
-
-    >>> # Accessing the model configuration
-    >>> configuration = model.config
-    ```"""
-    model_type = "internlm"
-    _auto_class = "AutoConfig"
-
-    def __init__(  # pylint: disable=W0102
-        self,
-        vocab_size=103168,
-        hidden_size=4096,
-        intermediate_size=11008,
-        num_hidden_layers=32,
-        num_attention_heads=32,
-        num_key_value_heads=None,
-        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,
-        tie_word_embeddings=False,
-        bias=True,
-        rope_theta=10000,
-        rope_scaling=None,
-        attn_implementation="eager",
-        **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
-        self.bias = bias
-
-        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.use_cache = use_cache
-        self.rope_theta = rope_theta
-        self.rope_scaling = rope_scaling
-        self._rope_scaling_validation()
-
-        self.attn_implementation = attn_implementation
-        if self.attn_implementation is None:
-            self.attn_implementation = "eager"
-        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 a float >= 1, got {rope_scaling_factor}")

tokenization_internlm.py

@@ -1,240 +0,0 @@
-# coding=utf-8
-# Copyright (c) InternLM. All rights reserved.
-#
-# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
-# and OPT implementations in this library. It has been modified from its
-# original forms to accommodate minor architectural differences compared
-# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Tokenization classes for IntermLM."""
-import os
-from shutil import copyfile
-from typing import Any, Dict, List, Optional, Tuple
-
-import sentencepiece as spm
-from transformers.tokenization_utils import PreTrainedTokenizer
-from transformers.utils import logging
-
-logger = logging.get_logger(__name__)
-
-VOCAB_FILES_NAMES = {"vocab_file": "./tokenizer.model"}
-
-PRETRAINED_VOCAB_FILES_MAP = {}
-
-
-class InternLMTokenizer(PreTrainedTokenizer):
-    """
-    Construct a InternLM tokenizer. Based on byte-level Byte-Pair-Encoding.
-
-    Args:
-        vocab_file (`str`):
-            Path to the vocabulary file.
-    """
-
-    vocab_files_names = VOCAB_FILES_NAMES
-    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
-    model_input_names = ["input_ids", "attention_mask"]
-    _auto_class = "AutoTokenizer"
-
-    def __init__(
-        self,
-        vocab_file,
-        unk_token="<unk>",
-        bos_token="<s>",
-        eos_token="</s>",
-        pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
-        add_bos_token=True,
-        add_eos_token=False,
-        decode_with_prefix_space=False,
-        clean_up_tokenization_spaces=False,
-        **kwargs,
-    ):
-        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
-        self.vocab_file = vocab_file
-        self.add_bos_token = add_bos_token
-        self.add_eos_token = add_eos_token
-        self.decode_with_prefix_space = decode_with_prefix_space
-        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
-        self.sp_model.Load(vocab_file)
-        self._no_prefix_space_tokens = None
-        super().__init__(
-            bos_token=bos_token,
-            eos_token=eos_token,
-            unk_token=unk_token,
-            pad_token=pad_token,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-
-        """ Initialization"""
-
-    @property
-    def no_prefix_space_tokens(self):
-        if self._no_prefix_space_tokens is None:
-            vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
-            self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith("▁")}
-        return self._no_prefix_space_tokens
-
-    @property
-    def vocab_size(self):
-        """Returns vocab size"""
-        return self.sp_model.get_piece_size()
-
-    @property
-    def bos_token_id(self) -> Optional[int]:
-        return self.sp_model.bos_id()
-
-    @property
-    def eos_token_id(self) -> Optional[int]:
-        return self.sp_model.eos_id()
-
-    def get_vocab(self):
-        """Returns vocab as a dict"""
-        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
-        vocab.update(self.added_tokens_encoder)
-        return vocab
-
-    def _tokenize(self, text):
-        """Returns a tokenized string."""
-        return self.sp_model.encode(text, out_type=str)
-
-    def _convert_token_to_id(self, token):
-        """Converts a token (str) in an id using the vocab."""
-        return self.sp_model.piece_to_id(token)
-
-    def _convert_id_to_token(self, index):
-        """Converts an index (integer) in a token (str) using the vocab."""
-        token = self.sp_model.IdToPiece(index)
-        return token
-
-    def _maybe_add_prefix_space(self, tokens, decoded):
-        if tokens and tokens[0] not in self.no_prefix_space_tokens:
-            return " " + decoded
-        else:
-            return decoded
-
-    def convert_tokens_to_string(self, tokens):
-        """Converts a sequence of tokens (string) in a single string."""
-        current_sub_tokens = []
-        out_string = ""
-        prev_is_special = False
-        for token in tokens:
-            # make sure that special tokens are not decoded using sentencepiece model
-            if token in self.all_special_tokens:
-                if not prev_is_special:
-                    out_string += " "
-                out_string += self.sp_model.decode(current_sub_tokens) + token
-                prev_is_special = True
-                current_sub_tokens = []
-            else:
-                current_sub_tokens.append(token)
-                prev_is_special = False
-        out_string += self.sp_model.decode(current_sub_tokens)
-        out_string = self.clean_up_tokenization(out_string)
-        out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
-        return out_string[1:]
-
-    def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
-        """
-        Save the vocabulary and special tokens file to a directory.
-
-        Args:
-            save_directory (`str`):
-                The directory in which to save the vocabulary.
-
-        Returns:
-            `Tuple(str)`: Paths to the files saved.
-        """
-        if not os.path.isdir(save_directory):
-            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
-            return
-        out_vocab_file = os.path.join(
-            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
-        )
-
-        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
-            copyfile(self.vocab_file, out_vocab_file)
-        elif not os.path.isfile(self.vocab_file):
-            with open(out_vocab_file, "wb") as fi:
-                content_spiece_model = self.sp_model.serialized_model_proto()
-                fi.write(content_spiece_model)
-
-        return (out_vocab_file,)
-
-    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
-        if self.add_bos_token:
-            bos_token_ids = [self.bos_token_id]
-        else:
-            bos_token_ids = []
-
-        output = bos_token_ids + token_ids_0
-
-        if token_ids_1 is not None:
-            output = output + token_ids_1
-
-        if self.add_eos_token:
-            output = output + [self.eos_token_id]
-
-        return output
-
-    def get_special_tokens_mask(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
-    ) -> List[int]:
-        """
-        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
-        special tokens using the tokenizer `prepare_for_model` method.
-
-        Args:
-            token_ids_0 (`List[int]`):
-                List of IDs.
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
-                Whether or not the token list is already formatted with special tokens for the model.
-
-        Returns:
-            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
-        """
-        if already_has_special_tokens:
-            return super().get_special_tokens_mask(
-                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
-            )
-
-        if token_ids_1 is None:
-            return [1] + ([0] * len(token_ids_0)) + [1]
-        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
-
-    def create_token_type_ids_from_sequences(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
-        use of token type ids, therefore a list of zeros is returned.
-
-        Args:
-            token_ids_0 (`List[int]`):
-                List of IDs.
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-
-        Returns:
-            `List[int]`: List of zeros.
-        """
-        eos = [self.eos_token_id]
-
-        if token_ids_1 is None:
-            return len(token_ids_0 + eos) * [0]
-        return len(token_ids_0 + eos + token_ids_1 + eos) * [0]