|
{ |
|
"add_special_tokens": false, |
|
"architectures": [ |
|
"T5VaeForAutoencoding" |
|
], |
|
"config_path": null, |
|
"decoder_start_token_id": 0, |
|
"dtype": "float32", |
|
"eos_token_id": 1, |
|
"latent_token_size": 2, |
|
"model_name_or_path": null, |
|
"model_type": "transformer_vae", |
|
"n_latent_tokens": 16, |
|
"pad_token_id": 0, |
|
"set_seq_size": 60, |
|
"t5": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"T5WithLMHeadModel" |
|
], |
|
"bad_words_ids": null, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"d_ff": 3072, |
|
"d_kv": 64, |
|
"d_model": 768, |
|
"decoder_start_token_id": 0, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"dropout_rate": 0.1, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": 1, |
|
"feed_forward_proj": "relu", |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"gradient_checkpointing": false, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"initializer_factor": 1.0, |
|
"is_decoder": false, |
|
"is_encoder_decoder": true, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"layer_norm_epsilon": 1e-06, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "t5", |
|
"n_positions": 512, |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_decoder_layers": 12, |
|
"num_heads": 12, |
|
"num_layers": 12, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_past": true, |
|
"output_scores": false, |
|
"pad_token_id": 0, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"relative_attention_num_buckets": 32, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"task_specific_params": { |
|
"summarization": { |
|
"early_stopping": true, |
|
"length_penalty": 2.0, |
|
"max_length": 200, |
|
"min_length": 30, |
|
"no_repeat_ngram_size": 3, |
|
"num_beams": 4, |
|
"prefix": "summarize: " |
|
}, |
|
"translation_en_to_de": { |
|
"early_stopping": true, |
|
"max_length": 300, |
|
"num_beams": 4, |
|
"prefix": "translate English to German: " |
|
}, |
|
"translation_en_to_fr": { |
|
"early_stopping": true, |
|
"max_length": 300, |
|
"num_beams": 4, |
|
"prefix": "translate English to French: " |
|
}, |
|
"translation_en_to_ro": { |
|
"early_stopping": true, |
|
"max_length": 300, |
|
"num_beams": 4, |
|
"prefix": "translate English to Romanian: " |
|
} |
|
}, |
|
"temperature": 1.0, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": null, |
|
"torchscript": false, |
|
"transformers_version": "4.9.0.dev0", |
|
"use_bfloat16": false, |
|
"use_cache": true, |
|
"vocab_size": 32100 |
|
}, |
|
"tokenizer_name": null, |
|
"transformers_version": null, |
|
"use_cache": true, |
|
"use_fast_tokenizer": true, |
|
"vae_decoder_model": "", |
|
"vae_encoder_model": "", |
|
"vocab_size": 32100 |
|
} |
|
|