File size: 1,934 Bytes
89d090e |
1 |
{"decoder": {"classifier_dropout": 0.0, "d_ff": 37, "d_kv": 8, "d_model": 32, "decoder_start_token_id": 0, "dense_act_fn": "relu", "dropout_rate": 0.1, "feed_forward_proj": "relu", "gradient_checkpointing": false, "initializer_factor": 0.002, "is_encoder_decoder": true, "is_gated_act": false, "layer_norm_epsilon": 1e-06, "model_type": "t5", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_num_beams": 1, "static_sequence_length": 64}, "num_decoder_layers": 5, "num_heads": 4, "num_layers": 5, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 8, "task": "text2text-generation", "use_cache": true, "vocab_size": 1103}, "encoder": {"classifier_dropout": 0.0, "d_ff": 37, "d_kv": 8, "d_model": 32, "decoder_start_token_id": 0, "dense_act_fn": "relu", "dropout_rate": 0.1, "feed_forward_proj": "relu", "gradient_checkpointing": false, "initializer_factor": 0.002, "is_encoder_decoder": true, "is_gated_act": false, "layer_norm_epsilon": 1e-06, "model_type": "t5", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_num_beams": 1, "static_sequence_length": 64}, "num_decoder_layers": 5, "num_heads": 4, "num_layers": 5, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 8, "task": "text2text-generation", "use_cache": true, "vocab_size": 1103}, "model_type": "t5"} |