Upload tokenizer

README.md

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 datasets:
 - llm-jp/oasst1-21k-ja
 - llm-jp/oasst2-33k-ja
@@ -14,6 +13,7 @@ datasets:
 - Manual-Dataset-Creation-Project/Malum-130
 - sudy-super/CoTangent
 - minnade/chat-daily
+license: apache-2.0
 ---
 # Yamase-12B
 ### Description

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}