Null77/results
04
1{2 "architectures": [3 "T5ForConditionalGeneration"4 ],5 "classifier_dropout": 0.0,6 "d_ff": 3072,7 "d_kv": 64,8 "d_model": 768,9 "decoder_start_token_id": 0,10 "dense_act_fn": "relu",11 "dropout_rate": 0.1,12 "eos_token_id": 1,13 "feed_forward_proj": "relu",14 "initializer_factor": 1.0,15 "is_encoder_decoder": true,16 "is_gated_act": false,17 "layer_norm_epsilon": 1e-06,18 "model_type": "t5",19 "n_positions": 512,20 "num_decoder_layers": 12,21 "num_heads": 12,22 "num_layers": 12,23 "output_past": true,24 "pad_token_id": 0,25 "relative_attention_max_distance": 128,26 "relative_attention_num_buckets": 32,27 "task_specific_params": {28 "summarization": {29 "early_stopping": true,30 "length_penalty": 2.0,31 "max_length": 200,32 "min_length": 30,33 "no_repeat_ngram_size": 3,34 "num_beams": 4,35 "prefix": "summarize: "36 },37 "translation_en_to_de": {38 "early_stopping": true,39 "max_length": 300,40 "num_beams": 4,41 "prefix": "translate English to German: "42 },43 "translation_en_to_fr": {44 "early_stopping": true,45 "max_length": 300,46 "num_beams": 4,47 "prefix": "translate English to French: "48 },49 "translation_en_to_ro": {50 "early_stopping": true,51 "max_length": 300,52 "num_beams": 4,53 "prefix": "translate English to Romanian: "54 }55 },56 "torch_dtype": "float32",57 "transformers_version": "4.54.0",58 "use_cache": true,59 "vocab_size": 3212860}61 