configuration_dimple.py

# coding=utf-8
# Copyright 2024 The Dimple team and the HuggingFace Inc. team. All rights reserved.
#
# 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.
"""Dimple model configuration"""

import os
from typing import Union

from transformers.configuration_utils import PretrainedConfig
from transformers.modeling_rope_utils import rope_config_validation
from transformers.utils import logging


logger = logging.get_logger("Dimple."+__name__)


class DimpleVisionConfig(PretrainedConfig):
    model_type = "dimple"

    def __init__(
        self,
        depth=32,
        hidden_size=1280,
        hidden_act="silu",
        intermediate_size=3420,
        num_heads=16,
        in_channels=3,
        patch_size=14,
        spatial_merge_size=2,
        temporal_patch_size=2,
        tokens_per_second=2,
        window_size=112,
        out_hidden_size=3584,
        fullatt_block_indexes=[7, 15, 23, 31],
        **kwargs,
    ):
        super().__init__(**kwargs)

        self.depth = depth
        self.hidden_size = hidden_size
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.num_heads = num_heads
        self.in_channels = in_channels
        self.patch_size = patch_size
        self.spatial_merge_size = spatial_merge_size
        self.temporal_patch_size = temporal_patch_size
        self.tokens_per_second = tokens_per_second
        self.window_size = window_size
        self.fullatt_block_indexes = fullatt_block_indexes
        self.out_hidden_size = out_hidden_size


    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
        cls._set_token_in_kwargs(kwargs)

        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)

        if config_dict.get("model_type") == "dimple":
            config_dict = config_dict["vision_config"]

        if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
            logger.warning(
                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
                f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
            )

        return cls.from_dict(config_dict, **kwargs)


class DimpleConfig(PretrainedConfig):
    model_type = "dimple"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=151936,
        hidden_size=4096,
        intermediate_size=22016,
        num_hidden_layers=32,
        num_attention_heads=32,
        num_key_value_heads=32,
        hidden_act="silu",
        max_position_embeddings=32768,
        initializer_range=0.02,
        image_token_id = 151655,
        video_token_id = 151656,
        vision_end_token_id = 151653,
        vision_start_token_id = 151652,
        vision_token_id = 151654,
        rms_norm_eps=1e-6,
        use_cache=False,  # cache not used in diffusion
        tie_word_embeddings=False,
        rope_theta=10000.0,
        use_sliding_window=False,
        sliding_window=4096,
        max_window_layers=28,
        attention_dropout=0.0,
        mask_token_id=151666,
        pad_token_id=151643,
        vision_config=None,
        rope_scaling=None,
        mrope_section=[16,24,24],
        full_attn_mask = True,
        **kwargs,
    ):
        if isinstance(vision_config, dict):
            self.vision_config = DimpleVisionConfig(**vision_config)
        elif vision_config is None:
            self.vision_config = DimpleVisionConfig()

        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.use_sliding_window = use_sliding_window
        self.sliding_window = sliding_window if use_sliding_window else None
        self.max_window_layers = max_window_layers

        # 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.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self.attention_dropout = attention_dropout
        # Validate the correctness of rotary position embeddings parameters
        # BC: if there is a 'type' field, move it to 'rope_type'.
        if self.rope_scaling is not None and "type" in self.rope_scaling:
            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
        rope_config_validation(self, ignore_keys={"mrope_section"})
        self.mrope_section = mrope_section
        
        super().__init__(
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )
        self.mask_token_id = mask_token_id
        self.pad_token_id = pad_token_id
        self.image_token_id = image_token_id
        self.video_token_id = video_token_id
        self.vision_end_token_id = vision_end_token_id
        self.vision_start_token_id = vision_start_token_id
        self.vision_token_id = vision_token_id
        self.full_attn_mask = full_attn_mask