You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
110 lines
5.3 KiB
110 lines
5.3 KiB
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# This file was automatically generated from src/transformers/models/glm46v/modular_glm46v.py.
|
|
# Do NOT edit this file manually as any edits will be overwritten by the generation of
|
|
# the file from the modular. If any change should be done, please apply the change to the
|
|
# modular_glm46v.py file directly. One of our CI enforces this.
|
|
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# Copyright 2025 the HuggingFace 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.
|
|
|
|
|
|
from ...configuration_utils import PreTrainedConfig
|
|
from ..auto import CONFIG_MAPPING, AutoConfig
|
|
|
|
|
|
class Glm46VConfig(PreTrainedConfig):
|
|
r"""
|
|
This is the configuration class to store the configuration of a [`Glm4vModel`]. It is used to instantiate a
|
|
GLM-4.6V model according to the specified arguments, defining the model architecture. Instantiating a
|
|
configuration with the defaults will yield a similar configuration to that of
|
|
GLM-4.1V-9B-Thinking [zai-org/GLM-4.1V-9B-Thinking](https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking).
|
|
|
|
Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
|
|
documentation from [`PreTrainedConfig`] for more information.
|
|
|
|
Args:
|
|
text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Glm4vTextConfig`):
|
|
The config object or dictionary of the text backbone.
|
|
vision_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Glm4vVisionConfig`):
|
|
The config object or dictionary of the vision backbone.
|
|
image_token_id (`int`, *optional*, defaults to 151343):
|
|
The image token index to encode the image prompt.
|
|
video_token_id (`int`, *optional*, defaults to 151344):
|
|
The video token index to encode the image prompt.
|
|
image_start_token_id (`int`, *optional*, defaults to 151339):
|
|
The image start token index to encode the start of image.
|
|
image_end_token_id (`int`, *optional*, defaults to 151340):
|
|
The image end token index to encode the end of image.
|
|
video_start_token_id (`int`, *optional*, defaults to 151361):
|
|
The video start token index to encode the start of video.
|
|
video_end_token_id (`int`, *optional*, defaults to 151362):
|
|
The video end token index to encode the end of video.
|
|
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
|
Whether to tie weight embeddings
|
|
|
|
```python
|
|
>>> from transformers import Glm46VForConditionalGeneration, Glm46VConfig
|
|
|
|
>>> # Initializing a GLM-4.6V style configuration
|
|
>>> configuration = Glm46VConfig()
|
|
|
|
>>> # Initializing a model from the GLM-4.6V style configuration
|
|
>>> model = Glm4vForConditionalGeneration(configuration)
|
|
|
|
>>> # Accessing the model configuration
|
|
>>> configuration = model.config
|
|
```"""
|
|
|
|
model_type = "glm46v"
|
|
sub_configs = {"text_config": AutoConfig, "vision_config": AutoConfig}
|
|
keys_to_ignore_at_inference = ["past_key_values"]
|
|
|
|
def __init__(
|
|
self,
|
|
text_config=None,
|
|
vision_config=None,
|
|
image_token_id=151343,
|
|
video_token_id=151344,
|
|
image_start_token_id=151339,
|
|
image_end_token_id=151340,
|
|
video_start_token_id=151361,
|
|
video_end_token_id=151362,
|
|
tie_word_embeddings=False,
|
|
**kwargs,
|
|
):
|
|
if isinstance(vision_config, dict):
|
|
vision_config["model_type"] = vision_config.get("model_type", "glm4v_vision")
|
|
self.vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config)
|
|
elif vision_config is None:
|
|
self.vision_config = CONFIG_MAPPING["glm4v_vision"]()
|
|
|
|
if isinstance(text_config, dict):
|
|
text_config["model_type"] = text_config.get("model_type", "glm4v_text")
|
|
self.text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
|
|
elif text_config is None:
|
|
self.text_config = CONFIG_MAPPING["glm4v_text"]()
|
|
|
|
self.image_token_id = image_token_id
|
|
self.video_token_id = video_token_id
|
|
self.video_start_token_id = video_start_token_id
|
|
self.video_end_token_id = video_end_token_id
|
|
self.image_start_token_id = image_start_token_id
|
|
self.image_end_token_id = image_end_token_id
|
|
self.tie_word_embeddings = tie_word_embeddings
|
|
|
|
super().__init__(**kwargs)
|
|
|
|
|
|
__all__ = ["Glm46VConfig"]
|