Upload tokenizer

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "</s>",
-  "unk_token": "<unk>"
+  "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
+  }
 }

tokenizer_config.json

@@ -23,22 +23,17 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32270": {
-      "content": "\t",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|उपयोगकर्ता|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|प्रणाली|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|सहायक|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|सहायक|>' }}\n{% endif %}\n{% endfor %}\n",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ bos_token + 'उपयोगकर्ता\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ bos_token + 'सहायक\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ bos_token + 'सहायक\n' }}\n{% endif %}\n{% endfor %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": false,
+  "model_max_length": 1024,
   "pad_token": "</s>",
+  "sp_model_kwargs": {},
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<unk>"
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }