Upload tokenizer from minimax_m1

.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 +1,24 @@
+{{ '<begin_of_document>' -}}{% set ns = namespace(system_prompt='') -%}{% for message in messages -%}{% if message['role'] == 'system' -%}{% set ns.system_prompt = ns.system_prompt + message['content'][0]['text'] -%}{% endif -%}{%- endfor -%}{% if ns.system_prompt != '' -%}{{ '<beginning_of_sentence>system ai_setting=assistant
+' + ns.system_prompt + '<end_of_sentence>
+' -}}{%- endif -%}{% if tools -%}{{ '<beginning_of_sentence>system tool_setting=tools
+You are provided with these tools:
+<tools>
+' -}}{% for tool in tools -%}{{ tool | tojson ~ '
+' -}}{%- endfor -%}{{ '</tools>
+
+If you need to call tools, please respond with <tool_calls></tool_calls> XML tags, and provide tool-name and json-object of arguments, following the format below:
+<tool_calls>
+{''name'': <tool-name-1>, ''arguments'': <args-json-object-1>}
+...
+</tool_calls><end_of_sentence>
+' -}}{%- endif -%}{% for message in messages -%}{% if message['role'] == 'user' -%}{{ '<beginning_of_sentence>user name=user
+' + message['content'][0]['text'] + '<end_of_sentence>
+' -}}{% elif message['role'] == 'assistant' -%}{{ '<beginning_of_sentence>ai name=assistant
+' -}}{% for content in message['content'] | selectattr('type', 'equalto', 'text') -%}{{ content['text'] -}}{%- endfor -%}{{ '<end_of_sentence>
+' -}}{% elif message['role'] == 'tool' -%}{{ '<beginning_of_sentence>tool name=tools
+' }} {%- for content in message['content'] -%}{{- 'tool name: ' + content['name'] + '
+' + 'tool result: ' + content['text'] + '
+
+' -}} {%- endfor -%}{{- '<end_of_sentence>
+' -}}{% endif -%}{%- endfor -%}{% if add_generation_prompt -%}{{ '<beginning_of_sentence>ai name=assistant
+' -}}{%- endif -%}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f4201a1d9edc97b52b3927bd892299d129e5a54a92fe518f4a145715228f31
+size 15519168

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>"
+}