Upload tokenizer

chat_template.jinja

@@ -0,0 +1,147 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not documents_in_user_message is defined %}
+    {%- set documents_in_user_message = true %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not documents is defined %}
+    {%- set documents = none %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "December 2025" %}
+{%- 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 + documents + builtin tools + date #}
+{{- "<|start_header_id|>system<|end_header_id|>\n" }}
+{%- if documents is not none and not documents_in_user_message %}
+    {{- "You have access to the following documents. Please use them to answer the user's question." }}
+    {%- 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.\n\n" }}
+{%- endif %}
+{%- 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." }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. '}}
+    {{- "Do not use variables.\n\n" }}
+{%- endif %}
+
+{{- system_message }}
+{{- "<|end_of_text|>\n\n" }}
+
+
+{#- Custom tools and documents are passed in a user message with some extra guidance #}
+{%- if (documents_in_user_message and not documents is none) or (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 or documents in the first user message when there's no first user message!") }}
+    {%- endif %}
+
+    {{- '<|start_header_id|>user<|end_header_id|>\n' -}}
+
+    {#- Add documents to the user message if they are defined #}
+    {%- if documents_in_user_message and not documents is none %}
+        {{- "Given 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.\n\n" }}
+    {%- endif %}
+
+    {#- Add tools to the user message if they are defined #}
+    {%- if tools_in_user_message and not tools is none %}
+        {{- "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" }}
+        {%- for t in tools %}
+            {{- t | tojson(indent=4) }}
+            {{- "\n\n" }}
+        {%- endfor %}
+        {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. '}}
+        {{- "Do not use variables.\n\n" }}
+    {%- endif %}
+
+    {#- Add the first user message to the user message #}
+    {{- 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 %}

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": "<|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
+  }
+}