Upload tokenizer

special_tokens_map.json

@@ -11,13 +11,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|im_end|>",
   "pad_token": {
     "content": "<|end_of_text|>",
     "lstrip": false,

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -2073,7 +2073,7 @@
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] | trim + '<|im_end|>\n' }}{% endfor %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|im_end|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"