Upload tokenizer

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -1,109 +1,108 @@
-{{- 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 %}
-    {%- set date_string = "December 2024" %}
-{%- 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 + builtin tools #}
-{{- "<|start_header_id|>system<|end_header_id|>\n" }}
-{%- if builtin_tools is defined or tools is not none %}
-    {{- "Environment: ipython\n" }}
-{%- endif %}
-{%- if builtin_tools is defined %}
-    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
-{%- endif %}
-{{- "Cutting Knowledge Date: December 2024\n" }}
-{{- "Today Date: " + date_string + "\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" }}
-    {%- endfor %}
-{%- endif %}
-{{- system_message }}
-{{- "<|end_of_text|>\n\n" }}
-
-{#- 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:] %}
-    {%- 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' -}}
-    {{- "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 + "<|end_of_text|>\n\n"}}
-{%- 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'+ message['content'] | trim + '<|end_of_text|>\n\n' }}
-    {%- elif 'tool_calls' in message %}
-        {%- if not message.tool_calls|length == 1 %}
-            {{- raise_exception("This model only supports single tool-calls at once!") }}
-        {%- endif %}
-        {%- set tool_call = message.tool_calls[0].function %}
-        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
-            {{- '<|start_header_id|>assistant<|end_header_id|>\n' -}}
-            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
-            {%- for arg_name, arg_val in tool_call.arguments | items %}
-                {{- arg_name + '="' + arg_val + '"' }}
-                {%- if not loop.last %}
-                    {{- ", " }}
-                {%- endif %}
-                {%- endfor %}
-            {{- ")" }}
-        {%- else  %}
-            {{- '<|start_header_id|>assistant<|end_header_id|>\n' -}}
-            {{- '{"name": "' + tool_call.name + '", ' }}
-            {{- '"parameters": ' }}
-            {{- tool_call.arguments | tojson }}
-            {{- "}" }}
-        {%- endif %}
-        {%- if builtin_tools is defined %}
-            {#- This means we're in ipython mode #}
-            {{- "<|end_of_text|>\n\n" }}
-        {%- else %}
-            {{- "<|end_of_text|>\n\n" }}
-        {%- endif %}
-    {%- elif message.role == "tool" or message.role == "ipython" %}
-        {{- "<|start_header_id|>ipython<|end_header_id|>\n" }}
-        {%- if message.content is mapping or message.content is iterable %}
-            {{- message.content | tojson }}
-        {%- else %}
-            {{- message.content }}
-        {%- endif %}
-        {{- "<|end_of_text|>\n\n" }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|start_header_id|>assistant<|end_header_id|>\n' }}
-{%- endif %}
+{%- if not documents is defined %}
+    {%- set documents = none %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+
+{#- 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 %}
+{%- else %}
+    {%- set system_message = "You are Doge, created by SmallDoge Team. You are a helpful assistant" %}
+{%- endif %}
+
+
+{#- system message + documents + tools #}
+{{- '<|im_start|>system\n' }}
+{{- system_message }}
+{%- if documents is not none %}
+    {{- "\n\nYou have access to the following documents. Please use them to answer the user's question.\n\n" }}
+    {%- for doc in documents %}
+        {%- if doc.title is defined %}
+            {{- "Title: " + doc.title + "\n" }}
+        {%- endif %}
+        {{- "Content: " + doc.text + "\n\n" }}
+    {%- endfor %}
+    {{- "If the documents don't contain relevant information, rely on your general knowledge but acknowledge when you're doing so." }}
+{%- endif %}
+{%- if tools is not none %}
+    {{- "\n\nYou may call one or more functions to assist with the user query. You are provided with function signatures within <tools></tools> XML tags:\n\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\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>" }}
+{%- endif %}
+{{- "<|im_end|>\n" }}
+
+{%- 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" 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.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 %}
+            {%- 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') %}
+            {%- 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') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + 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 }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

special_tokens_map.json

@@ -1,23 +1,23 @@
-{
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|finetune_right_pad_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}