Add tokenizer

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
+size 4920706

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d163342a36b3ad1ea2f5f608e6bb2b2ff29bd453a41c4f52525a7ebc7c4b6a
+size 17210041

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json",
+  "tokenizer_class": "XGLMTokenizer",
+  "unk_token": "<unk>"
+}