blanchon/dc_flux_krea_diffusers
04
1{2 "architectures": [3 "T5EncoderModel"4 ],5 "classifier_dropout": 0.0,6 "d_ff": 10240,7 "d_kv": 64,8 "d_model": 4096,9 "decoder_start_token_id": 0,10 "dense_act_fn": "gelu_new",11 "dropout_rate": 0.1,12 "dtype": "bfloat16",13 "eos_token_id": 1,14 "feed_forward_proj": "gated-gelu",15 "initializer_factor": 1.0,16 "is_encoder_decoder": false,17 "is_gated_act": true,18 "layer_norm_epsilon": 1e-06,19 "model_type": "t5",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 "tie_word_embeddings": false,28 "transformers_version": "4.57.3",29 "use_cache": false,30 "vocab_size": 3212831}32 