Upload tokenizer

README.md

@@ -1,9 +1,9 @@
 ---
-license: apache-2.0
 datasets:
 - jan-hq/instruction-speech-v1
 language:
 - en
+license: apache-2.0
 tags:
 - sound language model
 ---

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}