Transformers
PyTorch
English
rag
Inference Endpoints
rag-token-base / config.json
Quentin Lhoest
use full wiki_dpr instead of dummy
798dbab
raw
history blame
4.55 kB
{
"architectures": [
"RagTokenForGeneration"
],
"dataset": "wiki_dpr",
"dataset_split": "train",
"do_deduplication": true,
"do_marginalize": false,
"doc_sep": " // ",
"exclude_bos_score": false,
"generator": {
"_num_labels": 3,
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_bias_logits": false,
"add_cross_attention": false,
"add_final_layer_norm": false,
"architectures": [
"BartModel",
"BartForMaskedLM",
"BartForSequenceClassification"
],
"attention_dropout": 0.0,
"bad_words_ids": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"classif_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 2,
"do_sample": false,
"dropout": 0.1,
"early_stopping": false,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"extra_pos_embeddings": 2,
"finetuning_task": null,
"force_bos_token_to_be_generated": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_decoder": false,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 1024,
"min_length": 0,
"model_type": "bart",
"no_repeat_ngram_size": 0,
"normalize_before": false,
"normalize_embedding": true,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_past": false,
"pad_token_id": 1,
"prefix": " ",
"pruned_heads": {},
"repetition_penalty": 1.0,
"return_dict": false,
"scale_embedding": false,
"static_position_embeddings": false,
"task_specific_params": {
"summarization": {
"early_stopping": true,
"length_penalty": 2.0,
"max_length": 142,
"min_length": 56,
"no_repeat_ngram_size": 3,
"num_beams": 4
}
},
"temperature": 1.0,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 50265,
"xla_device": null
},
"index_name": "exact",
"index_path": null,
"is_encoder_decoder": true,
"label_smoothing": 0.0,
"max_combined_length": 300,
"model_type": "rag",
"n_docs": 5,
"output_retrieved": false,
"passages_path": null,
"question_encoder": {
"add_cross_attention": false,
"architectures": [
"DPRQuestionEncoder"
],
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"decoder_start_token_id": null,
"do_sample": false,
"early_stopping": false,
"eos_token_id": null,
"finetuning_task": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "dpr",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"prefix": null,
"projection_dim": 0,
"pruned_heads": {},
"repetition_penalty": 1.0,
"return_dict": false,
"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": 2,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 30522,
"xla_device": null
},
"reduce_loss": false,
"retrieval_batch_size": 8,
"retrieval_vector_size": 768,
"title_sep": " / ",
"use_dummy_dataset": false,
"vocab_size": null
}