Update config.json

config.json

@@ -0,0 +1,195 @@
+{
+  "architectures": [
+    "RagSequenceForGeneration"
+  ],
+  "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": [
+      "BartForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.0,
+    "d_model": 24,
+    "decoder_attention_heads": 2,
+    "decoder_ffn_dim": 16,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 2,
+    "decoder_start_token_id": 2,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 2,
+    "encoder_ffn_dim": 16,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 2,
+    "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": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "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,
+        "max_length": 10,
+        "min_length": 2,
+        "num_beams": 1
+      }
+    },
+    "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": "compressed",
+  "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": {
+    "_num_labels": 9,
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForTokenClassification"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "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": 2,
+    "id2label": {
+      "0": "O",
+      "1": "B-MISC",
+      "2": "I-MISC",
+      "3": "B-PER",
+      "4": "I-PER",
+      "5": "B-ORG",
+      "6": "I-ORG",
+      "7": "B-LOC",
+      "8": "I-LOC"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "B-LOC": 7,
+      "B-MISC": 1,
+      "B-ORG": 5,
+      "B-PER": 3,
+      "I-LOC": 8,
+      "I-MISC": 2,
+      "I-ORG": 6,
+      "I-PER": 4,
+      "O": 0
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 2,
+    "num_beams": 1,
+    "num_hidden_layers": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "prefix": null,
+    "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": 28996,
+    "xla_device": null
+  },
+  "reduce_loss": false,
+  "retrieval_batch_size": 8,
+  "retrieval_vector_size": 768,
+  "title_sep": " / ",
+  "use_dummy_dataset": false,
+  "vocab_size": null
+}