| { |
| "classifier_dropout": 0.0, |
| "d_ff": 2048, |
| "d_kv": 64, |
| "d_model": 512, |
| "dense_act_fn": "relu", |
| "dropout_rate": 0.1, |
| "eos_token_id": 1, |
| "feed_forward_proj": "relu", |
| "initializer_factor": 1.0, |
| "is_encoder_decoder": true, |
| "is_gated_act": false, |
| "layer_norm_epsilon": 1e-06, |
| "model_type": "t5", |
| "num_decoder_layers": 6, |
| "num_heads": 8, |
| "num_layers": 6, |
| "pad_token_id": 0, |
| "relative_attention_max_distance": 128, |
| "relative_attention_num_buckets": 32, |
| "transformers_version": "4.57.6", |
| "use_cache": true, |
| "vocab_size": 32128 |
| } |
|
|
