| { | |
| "architectures": [ | |
| "T5MIMOForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_t5mimo.T5MIMOConfig", | |
| "AutoModel": "modeling_t5mimo.T5MIMOModel", | |
| "AutoModelForSeq2SeqLM": "modeling_t5mimo.T5MIMOForConditionalGeneration" | |
| }, | |
| "classifier_dropout": 0.0, | |
| "d_ff": 1024, | |
| "d_kv": 64, | |
| "d_model": 256, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "relu", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "relu", | |
| "initializer_factor": 0.05, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": false, | |
| "is_mimo": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5mimo", | |
| "num_decoder_layers": 4, | |
| "num_filters": 64, | |
| "num_heads": 4, | |
| "num_layers": 4, | |
| "num_seqs": 3, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.41.1", | |
| "use_cache": true, | |
| "vocab_size": 4096 | |
| } | |