Upload model

config.json

@@ -4,13 +4,15 @@
     "EncoderDecoderModel"
   ],
   "decoder": {
-    "_name_or_path": "",
+    "_name_or_path": "roberta-base",
     "add_cross_attention": true,
-    "architectures": null,
-    "attention_probs_dropout_prob": 0,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": null,
+    "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
     "classifier_dropout": null,
     "cross_attention_hidden_size": null,
@@ -19,43 +21,42 @@
     "do_sample": false,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
+    "eos_token_id": 2,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
-    "hidden_dropout_prob": 0,
-    "hidden_size": 896,
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_range": 0.02,
-    "intermediate_size": 2240,
+    "intermediate_size": 3072,
     "is_decoder": true,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-12,
+    "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 2048,
+    "max_position_embeddings": 514,
     "min_length": 0,
-    "model_type": "bert",
+    "model_type": "roberta",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 7,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 7,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 0,
-    "position_embed_type": "relative_key_query",
+    "pad_token_id": 1,
     "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
@@ -76,20 +77,22 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "type_vocab_size": 2,
+    "type_vocab_size": 1,
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
     "vocab_size": 52305
   },
   "encoder": {
-    "_name_or_path": "",
-    "add_cross_attention": true,
-    "architectures": null,
-    "attention_probs_dropout_prob": 0,
+    "_name_or_path": "roberta-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": null,
+    "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
     "classifier_dropout": null,
     "cross_attention_hidden_size": null,
@@ -98,43 +101,42 @@
     "do_sample": false,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
+    "eos_token_id": 2,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
-    "hidden_dropout_prob": 0,
-    "hidden_size": 896,
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
     "initializer_range": 0.02,
-    "intermediate_size": 2240,
-    "is_decoder": true,
+    "intermediate_size": 3072,
+    "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-12,
+    "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 2048,
+    "max_position_embeddings": 514,
     "min_length": 0,
-    "model_type": "bert",
+    "model_type": "roberta",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 7,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 7,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 0,
-    "position_embed_type": "relative_key_query",
+    "pad_token_id": 1,
     "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
@@ -155,7 +157,7 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "type_vocab_size": 2,
+    "type_vocab_size": 1,
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
@@ -163,6 +165,7 @@
   },
   "is_encoder_decoder": true,
   "model_type": "encoder-decoder",
+  "tie_encoder_decoder": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.2"
 }

generation_config.json

@@ -1,5 +1,7 @@
 {
   "_from_model_config": true,
-  "pad_token_id": 0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5426aa2b8f8c66b153a08519df021bc0f5e47880175def3db80c91df54c9600d
-size 981652956
+oid sha256:5919bce141058d04a7002ec93d8ce415b11a84db5ff2c22d054f1228c35e4a8b
+size 620935092