AbstractFramework/bernini-r-1.3B-diffusers-bf16
0155
1{2 "_name_or_path": "google/umt5-xxl",3 "architectures": [4 "UMT5EncoderModel"5 ],6 "classifier_dropout": 0.0,7 "d_ff": 10240,8 "d_kv": 64,9 "d_model": 4096,10 "decoder_start_token_id": 0,11 "dense_act_fn": "gelu_new",12 "dropout_rate": 0.1,13 "eos_token_id": 1,14 "feed_forward_proj": "gated-gelu",15 "initializer_factor": 1.0,16 "is_encoder_decoder": true,17 "is_gated_act": true,18 "layer_norm_epsilon": 1e-06,19 "model_type": "umt5",20 "num_decoder_layers": 24,21 "num_heads": 64,22 "num_layers": 24,23 "output_past": true,24 "pad_token_id": 0,25 "relative_attention_max_distance": 128,26 "relative_attention_num_buckets": 32,27 "scalable_attention": true,28 "tie_word_embeddings": false,29 "tokenizer_class": "T5Tokenizer",30 "torch_dtype": "float32",31 "transformers_version": "4.48.0.dev0",32 "use_cache": true,33 "vocab_size": 25638434}35 