Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 language:
 - en
-license: apache-2.0
 library_name: transformers
+license: apache-2.0
 tags:
 - unsloth
 - transformers
@@ -10,7 +10,6 @@ tags:
 - mistral-7b
 - mistral-instruct
 - instruct
-
 ---
 
 # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

tokenizer.json

@@ -6943,23 +6943,13 @@
       "special": true
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
-  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [

tokenizer_config.json

@@ -6173,7 +6173,7 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n    {%- set system_message = messages[0][\"content\"] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n{%- for message in loop_messages | rejectattr(\"role\", \"equalto\", \"tool\") | rejectattr(\"role\", \"equalto\", \"tool_results\") | selectattr(\"tool_calls\", \"undefined\") %}\n    {%- if (message[\"role\"] == \"user\") != (loop.index0 % 2 == 0) %}\n        {{- raise_exception(\"After the optional system message, conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif %}\n{%- endfor %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if message[\"role\"] == \"user\" %}\n        {%- if tools is not none and (message == user_messages[-1]) %}\n            {{- \"[AVAILABLE_TOOLS] [\" }}\n            {%- for tool in tools %}\n        {%- set tool = tool.function %}\n        {{- '{\"type\": \"function\", \"function\": {' }}\n        {%- for key, val in tool.items() if key != \"return\" %}\n            {%- if val is string %}\n            {{- '\"' + key + '\": \"' + val + '\"' }}\n            {%- else %}\n            {{- '\"' + key + '\": ' + val|tojson }}\n            {%- endif %}\n            {%- if not loop.last %}\n            {{- \", \" }}\n            {%- endif %}\n        {%- endfor %}\n        {{- \"}}\" }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- else %}\n                    {{- \"]\" }}\n                {%- endif %}\n            {%- endfor %}\n            {{- \"[/AVAILABLE_TOOLS]\" }}\n            {%- endif %}\n        {%- if loop.last and system_message is defined %}\n            {{- \"[INST] \" + system_message + \"\\n\\n\" + message[\"content\"] + \"[/INST]\" }}\n        {%- else %}\n            {{- \"[INST] \" + message[\"content\"] + \"[/INST]\" }}\n        {%- endif %}\n    {%- elif message[\"role\"] == \"tool_calls\" or message.tool_calls is defined %}\n        {%- if message.tool_calls is defined %}\n            {%- set tool_calls = message.tool_calls %}\n        {%- else %}\n            {%- set tool_calls = message.content %}\n        {%- endif %}\n        {{- \"[TOOL_CALLS] [\" }}\n        {%- for tool_call in tool_calls %}\n            {%- set out = tool_call.function|tojson %}\n            {{- out[:-1] }}\n            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n                {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n            {%- endif %}\n            {{- ', \"id\": \"' + tool_call.id + '\"}' }}\n            {%- if not loop.last %}\n                {{- \", \" }}\n            {%- else %}\n                {{- \"]\" + eos_token }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif message[\"role\"] == \"assistant\" %}\n        {{- \" \" + message[\"content\"] + eos_token}}\n    {%- elif message[\"role\"] == \"tool_results\" or message[\"role\"] == \"tool\" %}\n        {%- if message.content is defined and message.content.content is defined %}\n            {%- set content = message.content.content %}\n        {%- else %}\n            {%- set content = message.content %}\n        {%- endif %}\n        {{- '[TOOL_RESULTS] {\"content\": ' + content|string + \", \" }}\n        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n            {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n        {%- endif %}\n        {{- '\"call_id\": \"' + message.tool_call_id + '\"}[/TOOL_RESULTS]' }}\n    {%- else %}\n        {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,