Initial model V1

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "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",
+  "transformers_version": "4.4.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb8e5dc18acc10e570b09aabff6f66d0bc4012ee7af1d8eb33d3da0cdf37b75
+size 499069583

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}}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "unk_token": {
+    "content": "<unk>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true,
+    "__type": "AddedToken"
+  },
+  "bos_token": {
+    "content": "<s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true,
+    "__type": "AddedToken"
+  },
+  "eos_token": {
+    "content": "</s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true,
+    "__type": "AddedToken"
+  },
+  "add_prefix_space": false,
+  "errors": "replace",
+  "sep_token": {
+    "content": "</s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true,
+    "__type": "AddedToken"
+  },
+  "cls_token": {
+    "content": "<s>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true,
+    "__type": "AddedToken"
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true,
+    "__type": "AddedToken"
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "single_word": false,
+    "lstrip": true,
+    "rstrip": false,
+    "normalized": true,
+    "__type": "AddedToken"
+  },
+  "max_len": 512,
+  "special_tokens_map_file": null,
+  "name_or_path": "/gpfs/projects/bsc88/tools/corpus-utils-lm/17-06-2021-python/output/bne_es_output/roberta-2021-06-17-1849-3a6a-9c4f/train_tokenizer_output/train-tokenizer-2021-06-17-2216-3a6a-3cd6"
+}