Upload tokenizer

README.md

@@ -1,10 +1,10 @@
 ---
 license: other
-license_name: deepseek
+library_name: transformers
 datasets:
 - ise-uiuc/Magicoder-OSS-Instruct-75K
 - ise-uiuc/Magicoder-Evol-Instruct-110K
-library_name: transformers
+license_name: deepseek
 pipeline_tag: text-generation
 ---
 # 🎩 Magicoder: Source Code Is All You Need

tokenizer_config.json

@@ -180,6 +180,7 @@
     }
   },
   "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{bos_token}}{{'You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.\n\n'}}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n        {{ raise_exception('System messages are not allowed in this template.') }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'@@ Instruction\n' + message['content'] + '\n\n'}}\n        {%- else %}\n{{'@@ Response\n' + message['content'] + eos_token + '\n\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{{'@@ Response\n'}}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<｜end▁of▁sentence｜>",
   "legacy": true,
@@ -188,6 +189,5 @@
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,
-  "use_default_system_prompt": false,
-  "chat_template": "{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] + '\\n\\n' }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'@@ Instruction\\n' + message['content'] + '\\n\\n'}}\n        {%- else %}\n{{'@@ Response\\n' + message['content'] + '\\n' + eos_token + '\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}{% if add_generation_prompt %}{{ '@@ Response\n' }}{% endif %}"
+  "use_default_system_prompt": false
 }