Update tokenizer chat template with Socratic prompt

Socratic-Tutor-Qwen2.5_Hf-7.6B-Q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c83705ffd690e7a3e67b15e62b07e34e851f3d36a9f9c5927ab876fef38f3fa
-size 8098524960
+oid sha256:67204dc2fd69aa83038db5293537b33cdbc83ee18347d829cc0e7d9924e2c068
+size 135

added_tokens.json

@@ -1,24 +1,5 @@
 {
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
   "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
   "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
+  "<|im_start|>": 151644
 }

chat_template.jinja

@@ -1,53 +1 @@
-{%- if tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if messages[0]['role'] == 'system' %}
-        {{- messages[0]['content'] }}
-    {%- else %}
-        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
-    {%- endif %}
-    {{- "\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 %}
-    {{- "\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 %}
-        {{- '<|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 (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 %}
-        {{- '\n<tool_response>\n' }}
-        {{- message.content }}
-        {{- '\n</tool_response>' }}
-        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
-            {{- '<|im_end|>\n' }}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|im_start|>assistant\n' }}
-{%- endif %}
+{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '<|im_start|>system\n' + '''You are Socrates, a wise and patient tutor. Your goal is not to give answers, but to guide the user to their own understanding through a series of thoughtful questions. Respond to the user's statements by asking probing questions that challenge their assumptions, clarify their thinking, and lead them toward the correct conclusion. Never provide a direct answer unless explicitly asked.''' + '<|im_end|>\n' }}{% endif %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ed0c8b432f995343ddfaa49b71c261da3d7da0e82673319c86e5987d996b65
-size 4999266524
+oid sha256:a9d6181e1f4819efc3c2bd24962cf11e704f8dbda5824ee84a5946d1cc733f38
+size 135

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e4bca43d1418f640a25a957c1c409f71acec32b9e17384729ef84aec114f8c
-size 4877660776
+oid sha256:a73a3895fb4421f8edf0201284ef3da16f5d60a9eeb8a1bc2f6615216b7ea719
+size 135

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec54d22f8824fd17b25aba5c2184f55597acaf357a705f971944c52098aaf1fd
-size 2308120383
+oid sha256:c8d2b513f7dd9907b80c15e23de7049a8bc7f9ac4e25e80684174d93e7930d8c
+size 135

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a8ede3bcd9e651883367d050af943cbcb31e59f61be191a8fcc043d902e3a3
-size 4932751008
+oid sha256:acb77437208d2a61f1df3e0f9e60303ceb1f2e8a66e25537f8288a748a023adc
+size 135

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95feed944bdd0440bccf80ed31f3430f3b043aec138ce9708fb090bc4268141
-size 4330865200
+oid sha256:3818826e702cfdd0bb13cb48fc4c375609b3709ec8c62695095e1833ed39701f
+size 135

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
-size 1089994880
+oid sha256:36b455f5b40fc6c1b6e47259f40b4940a9364e634e66fccb2fec109a0cc92bdc
+size 135

special_tokens_map.json

@@ -1,18 +1,7 @@
 {
   "additional_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|>"
+    "<|im_end|>"
   ],
   "eos_token": {
     "content": "<|im_end|>",
@@ -22,7 +11,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|vision_pad|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "151643": {
@@ -25,183 +24,19 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "151646": {
-      "content": "<|object_ref_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151647": {
-      "content": "<|object_ref_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151648": {
-      "content": "<|box_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151649": {
-      "content": "<|box_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151650": {
-      "content": "<|quad_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151651": {
-      "content": "<|quad_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151652": {
-      "content": "<|vision_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151653": {
-      "content": "<|vision_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151654": {
-      "content": "<|vision_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151655": {
-      "content": "<|image_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151656": {
-      "content": "<|video_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151657": {
-      "content": "<tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151658": {
-      "content": "</tool_call>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151659": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151660": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151661": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151662": {
-      "content": "<|fim_pad|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151663": {
-      "content": "<|repo_name|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "151664": {
-      "content": "<|file_sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "additional_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|>"
+    "<|im_end|>"
   ],
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
-  "pad_token": "<|vision_pad|>",
-  "padding_side": "right",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

update_prompt.py

@@ -0,0 +1,31 @@
+from transformers import AutoTokenizer
+
+# Load the tokenizer from the Hub
+model_id = "Qwen/Qwen2-7B-Instruct"
+print(f"Loading tokenizer for '{model_id}' from the Hub...")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+# This is the key change: we're targeting the cloned repo for saving
+model_dir = "/workspace/socratic-tutor-qwen2.5"
+
+socratic_system_prompt = (
+    "You are Socrates, a wise and patient tutor. Your goal is not to give answers, "
+    "but to guide the user to their own understanding through a series of thoughtful questions. "
+    "Respond to the user's statements by asking probing questions that challenge their assumptions, "
+    "clarify their thinking, and lead them toward the correct conclusion. "
+    "Never provide a direct answer unless explicitly asked."
+)
+
+new_chat_template = (
+    "{% for message in messages %}"
+    "{% if loop.first and message['role'] != 'system' %}"
+    "{{ '<|im_start|>system\\n' + '''" + socratic_system_prompt + "''' + '<|im_end|>\\n' }}"
+    "{% endif %}"
+    "{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>\\n' }}"
+    "{% endfor %}"
+    "{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}"
+)
+
+tokenizer.chat_template = new_chat_template
+tokenizer.save_pretrained(model_dir)
+print(f"✅ Tokenizer in '{model_dir}' updated with the Socratic prompt.")