google-t5/t5-base
7932.5m
1{2 "architectures": [3 "T5ForConditionalGeneration"4 ],5 "d_ff": 3072,6 "d_kv": 64,7 "d_model": 768,8 "decoder_start_token_id": 0,9 "dropout_rate": 0.1,10 "eos_token_id": 1,11 "initializer_factor": 1.0,12 "is_encoder_decoder": true,13 "layer_norm_epsilon": 1e-06,14 "model_type": "t5",15 "n_positions": 512,16 "num_heads": 12,17 "num_layers": 12,18 "output_past": true,19 "pad_token_id": 0,20 "relative_attention_num_buckets": 32,21 "task_specific_params": {22 "summarization": {23 "early_stopping": true,24 "length_penalty": 2.0,25 "max_length": 200,26 "min_length": 30,27 "no_repeat_ngram_size": 3,28 "num_beams": 4,29 "prefix": "summarize: "30 },31 "translation_en_to_de": {32 "early_stopping": true,33 "max_length": 300,34 "num_beams": 4,35 "prefix": "translate English to German: "36 },37 "translation_en_to_fr": {38 "early_stopping": true,39 "max_length": 300,40 "num_beams": 4,41 "prefix": "translate English to French: "42 },43 "translation_en_to_ro": {44 "early_stopping": true,45 "max_length": 300,46 "num_beams": 4,47 "prefix": "translate English to Romanian: "48 }49 },50 "vocab_size": 3212851}52 