step 500

chat_template.jinja

@@ -15,38 +15,29 @@
     {%- endif %}
 {%- endif %}
 {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
-{%- for forward_message in messages %}
+{%- for message in messages[::-1] %}
     {%- set index = (messages|length - 1) - loop.index0 %}
-    {%- 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) %}
+    {%- 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 %}
 {%- for message in messages %}
+    {%- 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' + message.content + '<|im_end|>' + '\n' }}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "assistant" %}
-        {%- set content = message.content %}
         {%- set reasoning_content = '' %}
-        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+        {%- if message.reasoning_content is string %}
             {%- set reasoning_content = message.reasoning_content %}
         {%- else %}
-            {%- if '</think>' in message.content %}
-                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
-                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
-                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
             {%- endif %}
         {%- endif %}
         {%- if loop.index0 > ns.last_query_index %}
@@ -83,7 +74,7 @@
             {{- '<|im_start|>user' }}
         {%- endif %}
         {{- '\n<tool_response>\n' }}
-        {{- message.content }}
+        {{- content }}
         {{- '\n</tool_response>' }}
         {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
             {{- '<|im_end|>\n' }}

tokenizer_config.json

@@ -5,10 +5,24 @@
   "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": 40960,
-  "pad_token": "<|vision_pad|>",
-  "padding_side": "left",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null