mrm8488
/

roberta-med-small2roberta-med-small-finetuned-cnn_daily_mail-summarization

Summarization Transformers PyTorch Safetensors

English encoder-decoder text2text-generation Inference Endpoints

Model card Files Files and versions Community

roberta-med-small2roberta-med-small-finetuned-cnn_daily_mail-summarization / config.json

mrm8488's picture

Initial commit from mrm8488

e44ddea over 3 years ago

raw history blame

No virus

3.79 kB

	{
	"architectures": [
	"EncoderDecoderModel"
	],
	"decoder": {
	"_name_or_path": "nyu-mll/roberta-med-small-1M-1",
	"_num_labels": 2,
	"add_cross_attention": true,
	"architectures": [
	"RobertaForMaskedLM"
	],
	"attention_probs_dropout_prob": 0.1,
	"bad_words_ids": null,
	"bos_token_id": 0,
	"chunk_size_feed_forward": 0,
	"decoder_start_token_id": null,
	"do_sample": false,
	"early_stopping": false,
	"eos_token_id": 2,
	"finetuning_task": null,
	"gradient_checkpointing": false,
	"hidden_act": "gelu",
	"hidden_dropout_prob": 0.1,
	"hidden_size": 512,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 2048,
	"is_decoder": true,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_norm_eps": 1e-05,
	"length_penalty": 1.0,
	"max_length": 20,
	"max_position_embeddings": 514,
	"min_length": 0,
	"model_type": "roberta",
	"no_repeat_ngram_size": 0,
	"num_attention_heads": 8,
	"num_beams": 1,
	"num_hidden_layers": 6,
	"num_return_sequences": 1,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_past": true,
	"pad_token_id": 1,
	"position_embedding_type": "absolute",
	"prefix": null,
	"pruned_heads": {},
	"repetition_penalty": 1.0,
	"return_dict": true,
	"sep_token_id": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torchscript": false,
	"type_vocab_size": 1,
	"use_bfloat16": false,
	"vocab_size": 50265,
	"xla_device": null
	},
	"decoder_start_token_id": 0,
	"early_stopping": true,
	"encoder": {
	"_name_or_path": "nyu-mll/roberta-med-small-1M-1",
	"_num_labels": 2,
	"add_cross_attention": false,
	"architectures": [
	"RobertaForMaskedLM"
	],
	"attention_probs_dropout_prob": 0.1,
	"bad_words_ids": null,
	"bos_token_id": 0,
	"chunk_size_feed_forward": 0,
	"decoder_start_token_id": null,
	"do_sample": false,
	"early_stopping": false,
	"eos_token_id": 2,
	"finetuning_task": null,
	"gradient_checkpointing": false,
	"hidden_act": "gelu",
	"hidden_dropout_prob": 0.1,
	"hidden_size": 512,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 2048,
	"is_decoder": false,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_norm_eps": 1e-05,
	"length_penalty": 1.0,
	"max_length": 20,
	"max_position_embeddings": 514,
	"min_length": 0,
	"model_type": "roberta",
	"no_repeat_ngram_size": 0,
	"num_attention_heads": 8,
	"num_beams": 1,
	"num_hidden_layers": 6,
	"num_return_sequences": 1,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_past": true,
	"pad_token_id": 1,
	"position_embedding_type": "absolute",
	"prefix": null,
	"pruned_heads": {},
	"repetition_penalty": 1.0,
	"return_dict": true,
	"sep_token_id": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torchscript": false,
	"type_vocab_size": 1,
	"use_bfloat16": false,
	"vocab_size": 50265,
	"xla_device": null
	},
	"eos_token_id": 2,
	"is_encoder_decoder": true,
	"length_penalty": 2.0,
	"max_length": 142,
	"min_length": 56,
	"model_type": "encoder-decoder",
	"no_repeat_ngram_size": 3,
	"num_beams": 4,
	"vocab_size": 50265
	}