First version of the your-model-name model and tokenizer.

README.md

@@ -0,0 +1 @@
+hello

added_tokens.json

@@ -0,0 +1,11 @@
+{
+  "<BOS>": 50265,
+  "<EOS>": 50266,
+  "<PAD>": 50267,
+  "<action>": 50269,
+  "<drama>": 50270,
+  "<horror>": 50272,
+  "<sci_fi>": 50273,
+  "<superhero>": 50268,
+  "<thriller>": 50271
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50274
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7170a02a100d9b1647cda25ed78da622e649c9310bb653de83cb987e74d7bc8
+size 498891129

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    "<superhero>",
+    "<action>",
+    "<drama>",
+    "<thriller>",
+    "<horror>",
+    "<sci_fi>"
+  ],
+  "bos_token": "<BOS>",
+  "cls_token": "<s>",
+  "eos_token": "<EOS>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<PAD>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a1383f1ae87084355ec862f6337da3c285bbf66ae6c284203a6171cb8e5399
+size 3451