|
{ |
|
"_name_or_path": "roberta-base", |
|
"architectures": [ |
|
"SentenceClassificationModel" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"bos_token_id": 0, |
|
"classification_head": { |
|
"num_labels": 6, |
|
"pooling_method": "attention" |
|
}, |
|
"label_mapper": {"other": 0, "anecdote": 1, "statistics": 2, "testimony": 3, "assumption": 4, "common-ground": 5}, |
|
"classifier_dropout": null, |
|
"context_config": { |
|
"_name_or_path": "roberta-base", |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"RobertaForMaskedLM" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": 0, |
|
"chunk_size_feed_forward": 0, |
|
"classifier_dropout": null, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": 2, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"layer_norm_eps": 1e-05, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"max_position_embeddings": 120, |
|
"min_length": 0, |
|
"model_type": "roberta", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 2, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_hidden_layers": 2, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "absolute", |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"tf_legacy_loss": false, |
|
"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": "4.35.0", |
|
"type_vocab_size": 1, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"use_cache": true, |
|
"vocab_size": 50265 |
|
}, |
|
"context_layer": "transformer", |
|
"eos_token_id": 2, |
|
"frozen_layers": [ |
|
0, |
|
1, |
|
2, |
|
3, |
|
4, |
|
5, |
|
6, |
|
7, |
|
8, |
|
9 |
|
], |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 514, |
|
"model_type": "roberta", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "absolute", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.35.0", |
|
"type_vocab_size": 1, |
|
"use_cache": true, |
|
"vocab_size": 50265 |
|
} |
|
|