|
{ |
|
"_commit_hash": "2f582cd79ed5795b71539951d237945bc1c5ac7e", |
|
"_name_or_path": "hf-internal-testing/tiny-random-t5", |
|
"bos_token_id": 0, |
|
"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, |
|
"eos_token_id": 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": null, |
|
"auto_cast_type": null, |
|
"compiler_type": "neuronx-cc", |
|
"compiler_version": "2.12.54.0+f631c2365", |
|
"dynamic_batch_size": false, |
|
"input_names": [ |
|
"decoder_input_ids", |
|
"decoder_attention_mask", |
|
"encoder_hidden_states", |
|
"attention_mask", |
|
"beam_idx", |
|
"beam_scores" |
|
], |
|
"model_type": "t5-decoder", |
|
"optlevel": "2", |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_names": [ |
|
"next_token_scores", |
|
"next_tokens", |
|
"next_indices", |
|
"past.0.self.key", |
|
"past.1.self.key", |
|
"past.2.self.key", |
|
"past.3.self.key", |
|
"past.4.self.key", |
|
"past.0.self.value", |
|
"past.1.self.value", |
|
"past.2.self.value", |
|
"past.3.self.value", |
|
"past.4.self.value", |
|
"past.0.cross.key", |
|
"past.1.cross.key", |
|
"past.2.cross.key", |
|
"past.3.cross.key", |
|
"past.4.cross.key", |
|
"past.0.cross.value", |
|
"past.1.cross.value", |
|
"past.2.cross.value", |
|
"past.3.cross.value", |
|
"past.4.cross.value" |
|
], |
|
"static_batch_size": 1, |
|
"static_num_beams": 4, |
|
"static_sequence_length": 18 |
|
}, |
|
"num_decoder_layers": 5, |
|
"num_heads": 4, |
|
"num_layers": 5, |
|
"pad_token_id": 0, |
|
"relative_attention_max_distance": 128, |
|
"relative_attention_num_buckets": 8, |
|
"task": "text2text-generation", |
|
"torchscript": true, |
|
"transformers_version": "4.11.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 1103 |
|
} |
|
|