Upload tokenizer

chat_template.jinja

@@ -1,90 +1,34 @@
-{%- set image_count = namespace(value=0) %}
-{%- set video_count = namespace(value=0) %}
-{%- macro render_content(content, do_vision_count, is_system_content=false) %}
-    {%- if content is string %}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping %}
-        {%- for item in content %}
-            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain images.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set image_count.value = image_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
-            {%- elif 'video' in item or item.type == 'video' %}
-                {%- if is_system_content %}
-                    {{- raise_exception('System message cannot contain videos.') }}
-                {%- endif %}
-                {%- if do_vision_count %}
-                    {%- set video_count.value = video_count.value + 1 %}
-                {%- endif %}
-                {%- if add_vision_id %}
-                    {{- 'Video ' ~ video_count.value ~ ': ' }}
-                {%- endif %}
-                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
-            {%- elif 'text' in item %}
-                {{- item.text }}
-            {%- else %}
-                {{- raise_exception('Unexpected item type in content.') }}
-            {%- endif %}
-        {%- endfor %}
-    {%- elif content is none or content is undefined %}
-        {{- '' }}
-    {%- else %}
-        {{- raise_exception('Unexpected content type.') }}
-    {%- endif %}
-{%- endmacro %}
-{%- if not messages %}
-    {{- raise_exception('No messages provided.') }}
-{%- endif %}
-{%- if tools and tools is iterable and tools is not mapping %}
+{%- if tools %}
     {{- '<|im_start|>system\n' }}
-    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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 %}
-    {{- "\n</tools>" }}
-    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
-    {%- if messages[0].role == 'system' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {%- if content %}
-            {{- '\n\n' + content }}
-        {%- endif %}
-    {%- endif %}
-    {{- '<|im_end|>\n' }}
+    {{- "\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' %}
-        {%- set content = render_content(messages[0].content, false, true)|trim %}
-        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
 {%- for message in messages[::-1] %}
     {%- set index = (messages|length - 1) - loop.index0 %}
-    {%- if ns.multi_step_tool and message.role == "user" %}
-        {%- set content = render_content(message.content, false)|trim %}
-        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
-            {%- set ns.multi_step_tool = false %}
-            {%- set ns.last_query_index = index %}
-        {%- endif %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
     {%- endif %}
 {%- endfor %}
-{%- if ns.multi_step_tool %}
-    {{- raise_exception('No user query found in messages.') }}
-{%- endif %}
 {%- for message in messages %}
-    {%- set content = render_content(message.content, true)|trim %}
-    {%- if message.role == "system" %}
-        {%- if not loop.first %}
-            {{- raise_exception('System message must be at the beginning.') }}
-        {%- endif %}
-    {%- elif message.role == "user" %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
         {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
         {%- set reasoning_content = '' %}
@@ -96,59 +40,50 @@
                 {%- set content = content.split('</think>')[-1].lstrip('\n') %}
             {%- endif %}
         {%- endif %}
-        {%- set reasoning_content = reasoning_content|trim %}
         {%- if loop.index0 > ns.last_query_index %}
-            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
         {%- else %}
             {{- '<|im_start|>' + message.role + '\n' + content }}
         {%- endif %}
-        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+        {%- if message.tool_calls %}
             {%- for tool_call in message.tool_calls %}
-                {%- if tool_call.function is defined %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
                     {%- set tool_call = tool_call.function %}
                 {%- endif %}
-                {%- if loop.first %}
-                    {%- if content|trim %}
-                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- else %}
-                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                    {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
                 {%- else %}
-                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
-                {%- endif %}
-                {%- if tool_call.arguments is defined %}
-                    {%- for args_name, args_value in tool_call.arguments|items %}
-                        {{- '<parameter=' + args_name + '>\n' }}
-                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
-                        {{- args_value }}
-                        {{- '\n</parameter>\n' }}
-                    {%- endfor %}
+                    {{- tool_call.arguments | tojson }}
                 {%- endif %}
-                {{- '</function>\n</tool_call>' }}
+                {{- '}\n</tool_call>' }}
             {%- endfor %}
         {%- endif %}
         {{- '<|im_end|>\n' }}
     {%- elif message.role == "tool" %}
-        {%- if loop.previtem and loop.previtem.role != "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}
         {%- endif %}
         {{- '\n<tool_response>\n' }}
         {{- content }}
         {{- '\n</tool_response>' }}
-        {%- if not loop.last and loop.nextitem.role != "tool" %}
-            {{- '<|im_end|>\n' }}
-        {%- elif loop.last %}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
             {{- '<|im_end|>\n' }}
         {%- endif %}
-    {%- else %}
-        {{- raise_exception('Unexpected message role.') }}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
     {{- '<|im_start|>assistant\n' }}
     {%- if enable_thinking is defined and enable_thinking is false %}
         {{- '<think>\n\n</think>\n\n' }}
-    {%- else %}
-        {{- '<think>\n' }}
     {%- endif %}
 {%- endif %}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
-size 19989325
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -1,32 +1,30 @@
 {
   "add_prefix_space": false,
-  "audio_bos_token": "<|audio_start|>",
-  "audio_eos_token": "<|audio_end|>",
-  "audio_token": "<|audio_pad|>",
   "backend": "tokenizers",
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "image_token": "<|image_pad|>",
+  "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,
   "local_files_only": false,
-  "model_max_length": 262144,
-  "model_specific_special_tokens": {
-    "audio_bos_token": "<|audio_start|>",
-    "audio_eos_token": "<|audio_end|>",
-    "audio_token": "<|audio_pad|>",
-    "image_token": "<|image_pad|>",
-    "video_token": "<|video_pad|>",
-    "vision_bos_token": "<|vision_start|>",
-    "vision_eos_token": "<|vision_end|>"
-  },
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
-  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null,
-  "video_token": "<|video_pad|>",
-  "vision_bos_token": "<|vision_start|>",
-  "vision_eos_token": "<|vision_end|>"
+  "unk_token": null
 }