Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,60 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Lowercase"
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "[PAD]": 0,
+      "[MASK]": 1,
+      "[UNK]": 2,
+      "a": 3,
+      "c": 4,
+      "g": 5,
+      "t": 6
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "/scratch/users/gbenegas/checkpoints/GPN_Arabidopsis_multispecies/ConvNet_batch2048_secondpart/checkpoint-30000",
+  "pad_token": "[PAD]",
+  "special_tokens_map_file": "/scratch/users/gbenegas/huggingface-cache/transformers/models--gonzalobenegas--tokenizer-dna-mlm/snapshots/fc3ac98b0909c87052bcd4ab241a23955cf3c046/special_tokens_map.json",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}