Bagheera Bghira
v1: from ptx0/coco-xltest, 36000 + 21800 + 14200 steps of mixed LAION/MJ dataset and offset noise with input perturbation on a probability of 25%, 10% caption dropout, cosine LR 4e-7 to 8e-7 every 3200 steps
90816e1
raw
history blame contribute delete
598 Bytes
{
"_name_or_path": "ptx0/sdxl-base",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.1",
"vocab_size": 49408
}