Upload folder using huggingface_hub

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391873f7bd3f2fd90e1b32839b1ff568cf27ea009815c8ba2d3c4c1c376bcd0d
+oid sha256:0fe561ece2a3a4d02534788071ac40015db9fafd7a50da77c570580c34798aeb
 size 604510743

special_tokens_map.json

@@ -1,36 +1,24 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<SMILES>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</SMILES>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<SEQ>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</SEQ>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<SMILES>",
+    "</SMILES>",
+    "<SEQ>",
+    "</SEQ>"
   ],
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
     "content": "[PAD]",
     "lstrip": false,
@@ -38,5 +26,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -84,8 +84,15 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
+  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }