add required files

config.json

@@ -1,5 +1,4 @@
 {
-  {
   "architectures": [
     "RagSequenceForGeneration"
   ],
@@ -9,45 +8,40 @@
   "do_marginalize": false,
   "doc_sep": " // ",
   "exclude_bos_score": false,
-  "forced_eos_token_id": 2,
   "generator": {
-    "_name_or_path": "facebook/bart-base",
-    "activation_dropout": 0.1,
+    "_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"
+      "BartModel",
+      "BartForMaskedLM",
+      "BartForSequenceClassification"
     ],
-    "attention_dropout": 0.1,
+    "attention_dropout": 0.0,
     "bad_words_ids": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
-    "classif_dropout": 0.1,
-    "classifier_dropout": 0.0,
-    "cross_attention_hidden_size": null,
-    "d_model": 768,
-    "decoder_attention_heads": 12,
-    "decoder_ffn_dim": 3072,
+    "classif_dropout": 0.0,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
     "decoder_layerdrop": 0.0,
-    "decoder_layers": 6,
+    "decoder_layers": 12,
     "decoder_start_token_id": 2,
-    "diversity_penalty": 0.0,
     "do_sample": false,
     "dropout": 0.1,
-    "early_stopping": true,
-    "encoder_attention_heads": 12,
-    "encoder_ffn_dim": 3072,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
     "encoder_layerdrop": 0.0,
-    "encoder_layers": 6,
-    "encoder_no_repeat_ngram_size": 0,
+    "encoder_layers": 12,
     "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
+    "extra_pos_embeddings": 2,
     "finetuning_task": null,
-    "forced_bos_token_id": 0,
-    "forced_eos_token_id": 2,
-    "gradient_checkpointing": false,
+    "force_bos_token_to_be_generated": false,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1",
@@ -66,44 +60,30 @@
     "max_position_embeddings": 1024,
     "min_length": 0,
     "model_type": "bart",
-    "no_repeat_ngram_size": 3,
+    "no_repeat_ngram_size": 0,
     "normalize_before": false,
     "normalize_embedding": true,
-    "num_beam_groups": 1,
-    "num_beams": 4,
-    "num_hidden_layers": 6,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
-    "output_scores": false,
+    "output_past": false,
     "pad_token_id": 1,
-    "prefix": null,
-    "problem_type": null,
+    "prefix": " ",
     "pruned_heads": {},
-    "remove_invalid_values": false,
     "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
+    "return_dict": false,
     "scale_embedding": false,
-    "sep_token_id": null,
+    "static_position_embeddings": false,
     "task_specific_params": {
       "summarization": {
-        "length_penalty": 1.0,
-        "max_length": 128,
-        "min_length": 12,
-        "num_beams": 4
-      },
-      "summarization_cnn": {
+        "early_stopping": true,
         "length_penalty": 2.0,
         "max_length": 142,
         "min_length": 56,
+        "no_repeat_ngram_size": 3,
         "num_beams": 4
-      },
-      "summarization_xsum": {
-        "length_penalty": 1.0,
-        "max_length": 62,
-        "min_length": 11,
-        "num_beams": 6
       }
     },
     "temperature": 1.0,
@@ -112,15 +92,13 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
     "torchscript": false,
-    "transformers_version": "4.19.2",
-    "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 50265
+    "vocab_size": 50265,
+    "xla_device": null
   },
-  "index_name": "pytorch_model.bin",
+  "index_name": "exact",
   "index_path": "MustEr/gpt2-elite",
   "is_encoder_decoder": true,
   "label_smoothing": 0.0,
@@ -130,7 +108,6 @@
   "output_retrieved": false,
   "passages_path": null,
   "question_encoder": {
-    "_name_or_path": "facebook/dpr-question_encoder-single-nq-base",
     "add_cross_attention": false,
     "architectures": [
       "DPRQuestionEncoder"
@@ -139,17 +116,11 @@
     "bad_words_ids": null,
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
-    "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": null,
-    "exponential_decay_length_penalty": null,
     "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "gradient_checkpointing": false,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.1,
@@ -174,24 +145,17 @@
     "model_type": "dpr",
     "no_repeat_ngram_size": 0,
     "num_attention_heads": 12,
-    "num_beam_groups": 1,
     "num_beams": 1,
     "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
-    "output_scores": false,
     "pad_token_id": 0,
-    "position_embedding_type": "absolute",
     "prefix": null,
-    "problem_type": null,
     "projection_dim": 0,
     "pruned_heads": {},
-    "remove_invalid_values": false,
     "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
+    "return_dict": false,
     "task_specific_params": null,
     "temperature": 1.0,
     "tie_encoder_decoder": false,
@@ -199,21 +163,17 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.19.2",
     "type_vocab_size": 2,
-    "typical_p": 1.0,
     "use_bfloat16": false,
-    "vocab_size": 30522
+    "use_cache": true,
+    "vocab_size": 30522,
+    "xla_device": null
   },
   "reduce_loss": false,
   "retrieval_batch_size": 8,
   "retrieval_vector_size": 768,
   "title_sep": " / ",
-  "torch_dtype": "float32",
-  "transformers_version": null,
-  "use_cache": true,
-  "use_dummy_dataset": true,
+  "use_dummy_dataset": false,
   "vocab_size": null
 }

generator_tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

generator_tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}

question_encoder_tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

question_encoder_tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "model_max_length": 512}