corrected to original config models

README.md

@@ -2,7 +2,7 @@
 
 Fine-tuning of a [question generator model](https://huggingface.co/mrm8488/bert2bert-spanish-question-generation) into a rephraser model using a poor-man's translation of the Quora question pairs dataset.
 
-- Original model: [mrm8488/bert2bert-spanish-question-generation](https://huggingface.co/mrm8488/bert2bert-spanish-question-generation?text=Manuel+vive+en+Murcia%2C+Espa%C3%B1a) 
+- Original models: [mrm8488/bert2bert-spanish-question-generation](https://huggingface.co/mrm8488/bert2bert-spanish-question-generation?text=Manuel+vive+en+Murcia%2C+Espa%C3%B1a), which is based on [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) (?).
 - Custom database: "Poor-man's"  translation of duplicated questions in Quora (translated with [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es))
 
 

config.json

@@ -1,12 +1,13 @@
 {
+  "_name_or_path": "model/bert2bert-spanish-paraphraser",
   "architectures": [
     "EncoderDecoderModel"
   ],
   "decoder": {
-    "_name_or_path": "/tmp/tmpm0i7404y",
+    "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
     "add_cross_attention": true,
     "architectures": [
-      "BertLMHeadModel"
+      "BertForMaskedLM"
     ],
     "attention_probs_dropout_prob": 0.1,
     "bad_words_ids": null,
@@ -73,7 +74,7 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
     "transformers_version": "4.18.0",
     "type_vocab_size": 2,
@@ -82,11 +83,13 @@
     "use_cache": true,
     "vocab_size": 31002
   },
+  "decoder_start_token_id": 4,
+  "early_stopping": true,
   "encoder": {
-    "_name_or_path": "/tmp/tmp617aadbn",
+    "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
     "add_cross_attention": false,
     "architectures": [
-      "BertModel"
+      "BertForMaskedLM"
     ],
     "attention_probs_dropout_prob": 0.1,
     "bad_words_ids": null,
@@ -153,7 +156,7 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
     "transformers_version": "4.18.0",
     "type_vocab_size": 2,
@@ -162,7 +165,16 @@
     "use_cache": true,
     "vocab_size": 31002
   },
+  "eos_token_id": 5,
   "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 128,
+  "min_length": 6,
   "model_type": "encoder-decoder",
-  "transformers_version": null
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vocab_size": 31002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4ae07744796cab593ae8515ed390f334b50ad666b84fe2805822ff5f943ebf0
-size 992592171
+oid sha256:b608c377fb4f55b935210920489a91e3fc1c13d9a5e02fc464b5e683ac48efe2
+size 992584811