Updated tokenizer with vocab size 32769

added_tokens.json

@@ -1,4 +1,3 @@
 {
-  "<eos>": 32769,
-  "[PAD]": 32768
+  "<tools>": 32768
 }

special_tokens_map.json

@@ -1,4 +1,13 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -6,14 +15,14 @@
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": "</s>",
-  "pad_token": {
-    "content": "[PAD]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -6944,16 +6944,7 @@
     },
     {
       "id": 32768,
-      "content": "[PAD]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32769,
-      "content": "<eos>",
+      "content": "<tools>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -6172,15 +6172,7 @@
       "special": true
     },
     "32768": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32769": {
-      "content": "<eos>",
+      "content": "<tools>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -6188,6 +6180,9 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<tools>"
+  ],
   "bos_token": "<s>",
   "chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n    {%- set system_message = messages[0][\"content\"] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n{%- set user_messages = loop_messages | selectattr(\"role\", \"equalto\", \"user\") | list %}\n\n{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}\n{%- set ns = namespace() %}\n{%- set ns.index = 0 %}\n{%- for message in loop_messages %}\n    {%- if not (message.role == \"tool\" or message.role == \"tool_results\" or (message.tool_calls is defined and message.tool_calls is not none)) %}\n        {%- if (message[\"role\"] == \"user\") != (ns.index % 2 == 0) %}\n            {{- raise_exception(\"After the optional system message, conversation roles must alternate user/assistant/user/assistant/...\") }}\n        {%- endif %}\n        {%- set ns.index = ns.index + 1 %}\n    {%- endif %}\n{%- endfor %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if message[\"role\"] == \"user\" %}\n        {%- if tools is not none and (message == user_messages[-1]) %}\n            {{- \"[AVAILABLE_TOOLS] [\" }}\n            {%- for tool in tools %}\n                {%- set tool = tool.function %}\n                {{- '{\"type\": \"function\", \"function\": {' }}\n                {%- for key, val in tool.items() if key != \"return\" %}\n                    {%- if val is string %}\n                        {{- '\"' + key + '\": \"' + val + '\"' }}\n                    {%- else %}\n                        {{- '\"' + key + '\": ' + val|tojson }}\n                    {%- endif %}\n                    {%- if not loop.last %}\n                        {{- \", \" }}\n                    {%- endif %}\n                {%- endfor %}\n                {{- \"}}\" }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- else %}\n                    {{- \"]\" }}\n                {%- endif %}\n            {%- endfor %}\n            {{- \"[/AVAILABLE_TOOLS]\" }}\n            {%- endif %}\n        {%- if loop.last and system_message is defined %}\n            {{- \"[INST] \" + system_message + \"\\n\\n\" + message[\"content\"] + \"[/INST]\" }}\n        {%- else %}\n            {{- \"[INST] \" + message[\"content\"] + \"[/INST]\" }}\n        {%- endif %}\n    {%- elif message.tool_calls is defined and message.tool_calls is not none %}\n        {{- \"[TOOL_CALLS] [\" }}\n        {%- for tool_call in message.tool_calls %}\n            {%- set out = tool_call.function|tojson %}\n            {{- out[:-1] }}\n            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}\n                {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n            {%- endif %}\n            {{- ', \"id\": \"' + tool_call.id + '\"}' }}\n            {%- if not loop.last %}\n                {{- \", \" }}\n            {%- else %}\n                {{- \"]\" + eos_token }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif message[\"role\"] == \"assistant\" %}\n        {{- \" \" + message[\"content\"]|trim + eos_token}}\n    {%- elif message[\"role\"] == \"tool_results\" or message[\"role\"] == \"tool\" %}\n        {%- if message.content is defined and message.content.content is defined %}\n            {%- set content = message.content.content %}\n        {%- else %}\n            {%- set content = message.content %}\n        {%- endif %}\n        {{- '[TOOL_RESULTS] {\"content\": ' + content|string + \", \" }}\n        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}\n            {{- raise_exception(\"Tool call IDs should be alphanumeric strings with length 9!\") }}\n        {%- endif %}\n        {{- '\"call_id\": \"' + message.tool_call_id + '\"}[/TOOL_RESULTS]' }}\n    {%- else %}\n        {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": false,
@@ -6195,7 +6190,7 @@
   "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",