| { | |
| "_name_or_path": "ssr-base", | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "d_ff": 3072, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dropout_rate": 0.1, | |
| "early_stopping": true, | |
| "eos_token_id": 1, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "length_penalty": 2.0, | |
| "max_length": 200, | |
| "min_length": 30, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "no_repeat_ngram_size": 3, | |
| "num_beams": 4, | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_num_buckets": 32, | |
| "save_step": 34, | |
| "vocab_size": 32128 | |
| } | |