Upload tokenizer

chat_template.jinja

@@ -1,30 +1,63 @@
+
 {%- if tools %}
-    {{- '<|im_start|>system\n' }}
+    {{- '<|im_start|>system
+' }}
     {%- if messages[0].role == 'system' %}
-        {{- messages[0].content + '\n\n' }}
+        {{- messages[0].content + '
+
+' }}
     {%- 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>" }}
+    {{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" }}
     {%- for tool in tools %}
-        {{- "\n" }}
+        {{- "
+" }}
         {{- tool | tojson }}
     {%- endfor %}
-    {{- "\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" }}
+    {{- "
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{\"name\": <function-name>, \"arguments\": <args-json-object>}
+</tool_call><|im_end|>
+" }}
 {%- else %}
     {%- if messages[0].role == 'system' %}
-        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+        {{- '<|im_start|>system
+' + messages[0].content + '<|im_end|>
+' }}
     {%- endif %}
 {%- endif %}
 {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for message in messages[::-1] %}
+{%- for forward_message in messages %}
     {%- set index = (messages|length - 1) - loop.index0 %}
-    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
         {%- set ns.multi_step_tool = false %}
         {%- set ns.last_query_index = index %}
     {%- endif %}
 {%- endfor %}
 {%- for message in messages %}
     {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
-        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+        {{- '<|im_start|>' + message.role + '
+' + message.content + '<|im_end|>' + '
+' }}
     {%- elif message.role == "assistant" %}
         {%- set content = message.content %}
         {%- set reasoning_content = '' %}
@@ -32,28 +65,43 @@
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
             {%- if '</think>' in message.content %}
-                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
-                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('
+') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('
+') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('
+') %}
             {%- endif %}
         {%- endif %}
         {%- if loop.index0 > ns.last_query_index %}
             {%- 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') }}
+                {{- '<|im_start|>' + message.role + '
+<think>
+' + reasoning_content.strip('
+') + '
+</think>
+
+' + content.lstrip('
+') }}
             {%- else %}
-                {{- '<|im_start|>' + message.role + '\n' + content }}
+                {{- '<|im_start|>' + message.role + '
+' + content }}
             {%- endif %}
         {%- else %}
-            {{- '<|im_start|>' + message.role + '\n' + content }}
+            {{- '<|im_start|>' + message.role + '
+' + content }}
         {%- endif %}
         {%- if message.tool_calls %}
             {%- for tool_call in message.tool_calls %}
                 {%- if (loop.first and content) or (not loop.first) %}
-                    {{- '\n' }}
+                    {{- '
+' }}
                 {%- endif %}
                 {%- if tool_call.function %}
                     {%- set tool_call = tool_call.function %}
                 {%- endif %}
-                {{- '<tool_call>\n{"name": "' }}
+                {{- '<tool_call>
+{"name": "' }}
                 {{- tool_call.name }}
                 {{- '", "arguments": ' }}
                 {%- if tool_call.arguments is string %}
@@ -61,25 +109,36 @@
                 {%- else %}
                     {{- tool_call.arguments | tojson }}
                 {%- endif %}
-                {{- '}\n</tool_call>' }}
+                {{- '}
+</tool_call>' }}
             {%- endfor %}
         {%- endif %}
-        {{- '<|im_end|>\n' }}
+        {{- '<|im_end|>
+' }}
     {%- elif message.role == "tool" %}
         {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
             {{- '<|im_start|>user' }}
         {%- endif %}
-        {{- '\n<tool_response>\n' }}
+        {{- '
+<tool_response>
+' }}
         {{- message.content }}
-        {{- '\n</tool_response>' }}
+        {{- '
+</tool_response>' }}
         {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
+            {{- '<|im_end|>
+' }}
         {%- endif %}
     {%- endif %}
 {%- endfor %}
 {%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
+    {{- '<|im_start|>assistant
+' }}
     {%- if enable_thinking is defined and enable_thinking is false %}
-        {{- '<think>\n\n</think>\n\n' }}
+        {{- '<think>
+
+</think>
+
+' }}
     {%- endif %}
-{%- endif %}
+{%- endif %}

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:c0acdaba32b920d640afb36af4396c91974e074735636e4016d17a8ed9c03730
+size 11422753

tokenizer_config.json

@@ -231,10 +231,14 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": 2048,
   "model_max_length": 512,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|vision_pad|>",
   "padding_side": "left",
   "split_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": null
 }