Upload tokenizer

chat_template.jinja

@@ -1,93 +1,54 @@
-{{- bos_token }}
-{%- if custom_tools is defined %}
-    {%- set tools = custom_tools %}
-{%- endif %}
-{%- if not tools_in_user_message is defined %}
-    {%- set tools_in_user_message = true %}
-{%- endif %}
-{%- if not date_string is defined %}
-    {%- if strftime_now is defined %}
-        {%- set date_string = strftime_now("%d %b %Y") %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
     {%- else %}
-        {%- set date_string = "26 Jul 2024" %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
     {%- endif %}
-{%- endif %}
-{%- if not tools is defined %}
-    {%- set tools = none %}
-{%- endif %}
-
-{#- This block extracts the system message, so we can slot it into the right place. #}
-{%- if messages[0]['role'] == 'system' %}
-    {%- set system_message = messages[0]['content']|trim %}
-    {%- set messages = messages[1:] %}
-{%- else %}
-    {%- set system_message = "" %}
-{%- endif %}
-
-{#- System message #}
-{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
-{%- if tools is not none %}
-    {{- "Environment: ipython\n" }}
-{%- endif %}
-{{- "Cutting Knowledge Date: December 2023\n" }}
-{{- "Today Date: " + date_string + "\n\n" }}
-{%- if tools is not none and not tools_in_user_message %}
-    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
-    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
-    {{- "Do not use variables.\n\n" }}
-    {%- for t in tools %}
-        {{- t | tojson(indent=4) }}
-        {{- "\n\n" }}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
     {%- endfor %}
-{%- endif %}
-{{- system_message }}
-{{- "<|eot_id|>" }}
-
-{#- Custom tools are passed in a user message with some extra guidance #}
-{%- if tools_in_user_message and not tools is none %}
-    {#- Extract the first user message so we can plug it in here #}
-    {%- if messages | length != 0 %}
-        {%- set first_user_message = messages[0]['content']|trim %}
-        {%- set messages = messages[1:] %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
     {%- else %}
-        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
-{%- endif %}
-    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
-    {{- "Given the following functions, please respond with a JSON for a function call " }}
-    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
-    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
-    {{- "Do not use variables.\n\n" }}
-    {%- for t in tools %}
-        {{- t | tojson(indent=4) }}
-        {{- "\n\n" }}
-    {%- endfor %}
-    {{- first_user_message + "<|eot_id|>"}}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
 {%- endif %}
-
 {%- for message in messages %}
-    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
-        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
-    {%- elif 'tool_calls' in message %}
-        {%- if not message.tool_calls|length == 1 %}
-            {{- raise_exception("This model only supports single tool-calls at once!") }}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
         {%- endif %}
-        {%- set tool_call = message.tool_calls[0].function %}
-        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
-        {{- '{"name": "' + tool_call.name + '", ' }}
-        {{- '"parameters": ' }}
-        {{- tool_call.arguments | tojson }}
-        {{- "}" }}
-        {{- "<|eot_id|>" }}
-    {%- elif message.role == "tool" or message.role == "ipython" %}
-        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
-        {%- if message.content is mapping or message.content is iterable %}
-            {{- message.content | tojson }}
-        {%- else %}
-            {{- message.content }}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
         {%- endif %}
-        {{- "<|eot_id|>" }}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+    {{- '<|im_start|>assistant\n' }}
 {%- endif %}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -1,13 +1,29 @@
 {
+  "add_prefix_space": false,
   "backend": "tokenizers",
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "is_local": false,
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
   ],
+  "is_local": false,
   "model_max_length": 131072,
-  "tokenizer_class": "TokenizersBackend"
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }