in jat/configuration_jat.py [0:0]
def __init__(
self,
vocab_size=50257,
max_position_embeddings=2048,
hidden_size=2048,
num_layers=24,
attention_types=[[["global", "local"], 12]],
num_heads=16,
intermediate_size=None,
window_size=256,
activation_function="gelu_new",
resid_dropout=0.0,
embed_dropout=0.0,
attention_dropout=0.0,
classifier_dropout=0.1,
layer_norm_epsilon=1e-5,
initializer_range=0.02,
use_cache=True,
bos_token_id=50256,
eos_token_id=50256,
max_continuous_size=377,
max_discrete_value=18,
image_size=224,
num_channels=3,
patch_size=16,
observation_loss_coef=0.005,
action_loss_coef=0.995,
**kwargs,