| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "bigscience/mt0-base", | |
| "encoder_dropout": 0.0, | |
| "encoder_hidden_size": 128, | |
| "encoder_num_layers": 2, | |
| "encoder_reparameterization_type": "MLP", | |
| "inference_mode": true, | |
| "num_attention_heads": 12, | |
| "num_layers": 12, | |
| "num_transformer_submodules": 2, | |
| "num_virtual_tokens": 10, | |
| "peft_type": "P_TUNING", | |
| "revision": null, | |
| "task_type": "SEQ_2_SEQ_LM", | |
| "token_dim": 768 | |
| } |