File size: 2,158 Bytes
42c6bee | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 | from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
class HCXVisionConfig(PretrainedConfig):
model_type = "hyperclovax_vlm"
keys_to_ignore_at_inference = ["past_key_values"]
# The `gpt2` class has a different name, so it needs to be updated accordingly.
language_config_attribute_map = {
"n_embd": "hidden_size",
"n_positions": "max_position_embeddings",
"n_head": "num_attention_heads",
"n_layer": "num_hidden_layers",
}
def __init__(
self,
language_config=None,
vision_config=None,
use_nth_layer=-2,
img_start_id=100009, # <|dummy3|>
decoder_max_length=4096,
anyres=False,
unpad=False,
max_num_grids=-1,
num_queries_vis_abstractor=-1,
ignore_index=-100,
proj_pos_emb=True,
proj_prenorm=False,
use_1x1_grid=False,
**kwargs,
):
for key, val in self.language_config_attribute_map.items():
if language_config is not None and key in language_config:
language_config[val] = language_config.pop(key)
self.language_config = language_config
self.vision_config = vision_config
if language_config is not None:
# In DeepSpeed ZeRO-3, the memory size is automatically determined based on the `hidden_size` specified in the config.
self.hidden_size = (
language_config["hidden_size"] if "hidden_size" in language_config else language_config["n_embd"]
)
# add VLM configs
self.use_nth_layer = use_nth_layer
self.decoder_max_length = decoder_max_length
self.anyres = anyres
self.unpad = unpad
self.max_num_grids = max_num_grids
self.num_queries_vis_abstractor = num_queries_vis_abstractor
self.img_start_id = img_start_id
self.ignore_index = ignore_index
self.proj_pos_emb = proj_pos_emb
self.proj_prenorm = proj_prenorm
self.use_1x1_grid = use_1x1_grid
super().__init__(**kwargs)
|