| { | |
| "architectures": ["T5ForConditionalGeneration"], | |
| "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, | |
| "layer_norm_epsilon": 1e-6, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 4, | |
| "num_heads": 4, | |
| "num_layers": 4, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.2", | |
| "use_cache": true, | |
| "vocab_size": 4096, | |
| "chronos_config": { | |
| "tokenizer_class": "MeanScaleUniformBins", | |
| "tokenizer_kwargs": { | |
| "low_limit": -15.0, | |
| "high_limit": 15.0 | |
| }, | |
| "n_tokens": 4096, | |
| "n_special_tokens": 2, | |
| "pad_token_id": 0, | |
| "eos_token_id": 1, | |
| "use_eos_token": true, | |
| "model_type": "seq2seq", | |
| "context_length": 512, | |
| "prediction_length": 64, | |
| "num_samples": 20, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0 | |
| } | |
| } | |