Upload tokenizer from minimax

.gitattributes

@@ -33,3 +33,4 @@ 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

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'system' %}{{ '<beginning_of_sentence>system ai_setting=assistant\n' + message['content'][0]['text'] + '<end_of_sentence>\n'}}{% elif message['role'] == 'user' %}{{ '<beginning_of_sentence>user name=user\n' + message['content'][0]['text'] + '<end_of_sentence>\n'}}{% elif message['role'] == 'assistant' %}{{ '<beginning_of_sentence>ai name=assistant\n' }}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{{ '<end_of_sentence>\n' }}{% elif message['role'] == 'function' %}{{ '<beginning_of_sentence>system function_response=functions\n' + '{"name": "' + message['name'] + '", "response": ' + message['content'][0]['text'] + '}' + '<end_of_sentence>\n'}}{% endif %}{% endfor %}{% if tools %}{% for function in tools %}{{ '<beginning_of_sentence>system function_setting=functions\n' + function | tojson + '<end_of_sentence>\n'}}{% endfor %}{% endif %}{% if add_generation_prompt %}{{ '<beginning_of_sentence>ai name=assistant\n' }}{% endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eca5e94e3f4a5ce117640723d37cd09d24a7056b19bd89b74c29191b77a5597
+size 15517253

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<beginning_of_sentence>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_sentence>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 40960000,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<end_of_document>"
+}