fix chat template

chat_template.jinja

@@ -0,0 +1,25 @@
+{%- set ns = namespace(has_head=true) -%}
+{%- set loop_messages = messages -%}
+{%- for message in loop_messages -%}
+    {%- set content = message['content'] -%}
+    {%- if loop.index0 == 0 -%}
+        {%- if content == '' -%}
+            {%- set ns.has_head = false -%}
+        {%- elif message['role'] == 'system' -%}
+            {%- set content = '<|startoftext|>' + content + '<|extra_4|>' -%}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if message['role'] == 'user' -%}
+        {%- if loop.index0 == 1 and not ns.has_head -%}
+            {%- set content = '<|startoftext|>' + content -%}
+        {%- endif -%}
+        {%- if loop.index0 == 1 and ns.has_head -%}
+            {%- set content = content + '<|extra_0|>' -%}
+        {%- else -%}
+            {%- set content = '<|startoftext|>' + content + '<|extra_0|>' -%}
+        {%- endif -%}
+    {%- elif message['role'] == 'assistant' -%}
+        {%- set content = content + '<|eos|>' -%}
+    {%- endif -%}
+    {{- content -}}
+{%- endfor -%}

tokenizer_config.json

@@ -4,6 +4,5 @@
   "eos_token": "<|eos|>",
   "model_max_length": 262144,
   "pad_token": "<|pad|>",
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "chat_template": "{% set context = {'has_head': true} %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = message['content'] %}{% if loop.index0 == 0 %}{% if content == '' %}{% set _ = context.update({'has_head': false}) %}{% elif message['role'] == 'system' %}{% set content = '<|startoftext|>' + content + '<|extra_4|>' %}{% endif %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 1 and not context.has_head %}{% set content = '<|startoftext|>' + content %}{% endif %}{% if loop.index0 == 1 and context.has_head %}{% set content = content + '<|extra_0|>' %}{% else %}{% set content = '<|startoftext|>' + content + '<|extra_0|>' %}{% endif %}{% elif message['role'] == 'assistant' %}{% set content = content + '<|eos|>' %}{% endif %}{{ content }}{% endfor %}"
-}
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}