Auto-upload tokenizer after eval at step 500

.gitattributes

@@ -33,3 +33,5 @@ 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
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,93 @@
+{{- 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 %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- 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 #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\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 }}
+{{- "<|eot_id|>" }}
+
+{#- 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\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 + "<|eot_id|>"}}
+{%- 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\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- 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 %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

special_tokens_map.json

@@ -0,0 +1,678 @@
+{
+  "additional_special_tokens": [
+    "<|start_audio|>",
+    "<|start_of_speech|>",
+    "<|start_phon_gen|>",
+    "<|end_phon_gen|>",
+    "<|GENERATE_PHONEMES_FROM_TEXT|>",
+    "<|GENERATE_TEXT_FROM_PHONEMES|>",
+    "<|ph_space|>",
+    "<|ph_0289|>",
+    "<|ph_025B-02E8-02E9|>",
+    "<|ph_0265|>",
+    "<|ph_0255-02B7|>",
+    "<|ph_0065-02D0-02E7-02E9|>",
+    "<|ph_0064-032A-02D0|>",
+    "<|ph_0075-02D0-02E9-02E9-02E6|>",
+    "<|ph_0076-02D0|>",
+    "<|ph_0250-0303|>",
+    "<|ph_0259-02E5|>",
+    "<|ph_007A-0329-02E7-02E5|>",
+    "<|ph_0075-0303|>",
+    "<|ph_028A|>",
+    "<|ph_0064-0292-02D0|>",
+    "<|ph_0065-006A|>",
+    "<|ph_0278-02B2|>",
+    "<|ph_0079-02E9|>",
+    "<|ph_0061-0077-02E5-02E9|>",
+    "<|ph_0259-02D0-02E8-02E9-02C0|>",
+    "<|ph_0075-02E9-02E9-02E6|>",
+    "<|ph_007A|>",
+    "<|ph_028A-02E5-02E9|>",
+    "<|ph_0075-02E8-02E9-02E6|>",
+    "<|ph_0264-02D0-02E9-02E9-02E6|>",
+    "<|ph_0254-02D0-02E8-02E9-02E8|>",
+    "<|ph_0075-0061-02E8-02E9|>",
+    "<|ph_00E7|>",
+    "<|ph_0254-02D0-02E8-02E9-02E6|>",
+    "<|ph_028F-02E9|>",
+    "<|ph_006F-0077-02E7|>",
+    "<|ph_006F-02D0-02E8-02E8|>",
+    "<|ph_0069-0259-02E8-02C0-02E5|>",
+    "<|ph_0069-0061-02E5-02E9|>",
+    "<|ph_0279|>",
+    "<|ph_0255-0348|>",
+    "<|ph_0254-02E5-02E9|>",
+    "<|ph_0074-02B7|>",
+    "<|ph_0069-02E8-02E8|>",
+    "<|ph_0074-0073|>",
+    "<|ph_0069|>",
+    "<|ph_006F-02E9-02E9-02E6|>",
+    "<|ph_026F-02D0-02E6-02E5|>",
+    "<|ph_0065-02D0-02E8-02E9-02E8|>",
+    "<|ph_0069-0259-02E8-02E6|>",
+    "<|ph_025B-02D0-02E7|>",
+    "<|ph_0070-0348-02B2|>",
+    "<|ph_0073|>",
+    "<|ph_0079-02E5|>",
+    "<|ph_0290|>",
+    "<|ph_0288-02B2|>",
+    "<|ph_007A-0329-02E7|>",
+    "<|ph_0254-02D0-02E8-02E6|>",
+    "<|ph_0070-02B2-02D0|>",
+    "<|ph_0069-02E9|>",
+    "<|ph_0061-02E5-02E7|>",
+    "<|ph_0061-0077-02E5|>",
+    "<|ph_0254-02D0-02E7|>",
+    "<|ph_006B-0348-02D0|>",
+    "<|ph_006F-02E8-02C0-02E5|>",
+    "<|ph_0268-02D0|>",
+    "<|ph_0073-0070-006E|>",
+    "<|ph_0066-02B2-02D0|>",
+    "<|ph_0259-0077|>",
+    "<|ph_0259-02E8-02E9-02E6|>",
+    "<|ph_0275-02E5-02E7|>",
+    "<|ph_0252-02D0|>",
+    "<|ph_007A-0329-02E8-02E9-02E6|>",
+    "<|ph_006F-0077-02E7-02E5|>",
+    "<|ph_0268-02E6-02E5|>",
+    "<|ph_026F-02E9-02E9-02E6|>",
+    "<|ph_0070-031A|>",
+    "<|ph_006B-02D0|>",
+    "<|ph_025F-02B7|>",
+    "<|ph_0251-02D0-02E9|>",
+    "<|ph_0275-02E9|>",
+    "<|ph_0064-02B2|>",
+    "<|ph_0261-02D0|>",
+    "<|ph_028E|>",
+    "<|ph_0073-0348-02B7|>",
+    "<|ph_025B-02D0-02E8-02E8|>",
+    "<|ph_0075-02D0-02E8-02E9|>",
+    "<|ph_0079|>",
+    "<|ph_0251-02D0-02E5-02E9|>",
+    "<|ph_0065-02D0-02E7|>",
+    "<|ph_0074-031A|>",
+    "<|ph_0065-02E8-02E8|>",
+    "<|ph_0289-02D0-02E5-02E7|>",
+    "<|ph_0069-02D0-02E8-02E9|>",
+    "<|ph_0075-02D0-02E8-02E9-02C0|>",
+    "<|ph_0078|>",
+    "<|ph_006B|>",
+    "<|ph_0259-02D0-02E8-02E9|>",
+    "<|ph_0069-02D0-02E8-02C0-02E5|>",
+    "<|ph_0064-0290-02D0|>",
+    "<|ph_006F-02E7|>",
+    "<|ph_0070-0066|>",
+    "<|ph_0282-02D0|>",
+    "<|ph_006F-02E8-02E9-02E6|>",
+    "<|ph_0268-02D0-02E8-02E9-02E8|>",
+    "<|ph_0259-02E9|>",
+    "<|ph_0061-02D0-02E8-02E9-02E6|>",
+    "<|ph_0268-02D0-02E8-02C0-02E5|>",
+    "<|ph_0254-02E5-02E7|>",
+    "<|ph_0061-006A|>",
+    "<|ph_007A-032A|>",
+    "<|ph_007A-02B2-02D0|>",
+    "<|ph_0063-0348|>",
+    "<|ph_0264-02E6-02E5|>",
+    "<|ph_0069-02E8-02E9|>",
+    "<|ph_0061-02E8-02C0-02E5|>",
+    "<|ph_0061-02D0-02E8-02E6|>",
+    "<|ph_0288-0282|>",
+    "<|ph_006F-02D0-02E8-02E6|>",
+    "<|ph_025B-02D0-02E8-02C0-02E5|>",
+    "<|ph_0073-02D0|>",
+    "<|ph_0072|>",
+    "<|ph_0065-02E5|>",
+    "<|ph_0061-02D0-02E8-02E9|>",
+    "<|ph_0064-032A-007A-032A-02D0|>",
+    "<|ph_0065-02D0-02E8-02E8|>",
+    "<|ph_0065-02E9|>",
+    "<|ph_0072-02D0|>",
+    "<|ph_0077-0303|>",
+    "<|ph_006D-0329-02E5|>",
+    "<|ph_026F-0061-02E7|>",
+    "<|ph_0064-0291|>",
+    "<|ph_025B-02E9|>",
+    "<|ph_00F8-02D0-02E5-02E7|>",
+    "<|ph_026F-0325|>",
+    "<|ph_025C-02D0|>",
+    "<|ph_0061-02D0-02E8-02E9-02C0|>",
+    "<|ph_025F|>",
+    "<|ph_0261|>",
+    "<|ph_027B|>",
+    "<|ph_0061-02E9-02E9-02E6|>",
+    "<|ph_0074-032A-02D0|>",
+    "<|ph_0270-0303|>",
+    "<|ph_025B-02D0-02E7-02E9|>",
+    "<|ph_027E-02B2|>",
+    "<|ph_0072-02B2|>",
+    "<|ph_006F-0077-02E5|>",
+    "<|ph_0074-032A|>",
+    "<|ph_0074-0255-0348-02D0|>",
+    "<|ph_0074-0283|>",
+    "<|ph_028F-02E5-02E9|>",
+    "<|ph_0064-007A|>",
+    "<|ph_0254-02D0-02E9-02E9-02E6|>",
+    "<|ph_0074-0255-02D0|>",
+    "<|ph_026F-02D0-02E5-02E9|>",
+    "<|ph_026F-02E6-02E5|>",
+    "<|ph_0065-006A-02E7-02E5|>",
+    "<|ph_006B-031A|>",
+    "<|ph_0290-0329|>",
+    "<|ph_0064|>",
+    "<|ph_006F-02D0|>",
+    "<|ph_0255-02D0|>",
+    "<|ph_0065-02D0-02E8-02E9-02E6|>",
+    "<|ph_0061-02D0-02E8-02E9-02E8|>",
+    "<|ph_0251-02D0|>",
+    "<|ph_0069-02D0-02E5-02E7|>",
+    "<|ph_0064-032A-007A-032A|>",
+    "<|ph_0069-02D0-02E7-02E9|>",
+    "<|ph_0075-02D0-02E8-02E8|>",
+    "<|ph_0075-02E8-02E6|>",
+    "<|ph_0078-02B7|>",
+    "<|ph_00F8-02D0-02E7-02E9|>",
+    "<|ph_006D-02B2|>",
+    "<|ph_007A-0329|>",
+    "<|ph_006D-0329-02E7|>",
+    "<|ph_006C|>",
+    "<|ph_00F8-02D0-02E5-02E9|>",
+    "<|ph_0065-02D0-02E8-02C0-02E5|>",
+    "<|ph_006F-02E7-02E5|>",
+    "<|ph_0061-0077-02E7-02E5|>",
+    "<|ph_006C-0329|>",
+    "<|ph_0065-02E8-02C0-02E5|>",
+    "<|ph_0061-0077-02E9|>",
+    "<|ph_0074-0073-02B2|>",
+    "<|ph_0268-0259-02E8-02E9-02E6|>",
+    "<|ph_025A|>",
+    "<|ph_0065-006A-02E5-02E9|>",
+    "<|ph_026F-02D0|>",
+    "<|ph_0073-02B2-02D0|>",
+    "<|ph_0282|>",
+    "<|ph_006A-02D0|>",
+    "<|ph_0254-02E8-02E9-02E8|>",
+    "<|ph_0275-02E5-02E9|>",
+    "<|ph_0076-02B7|>",
+    "<|ph_006F-02E6-02E5|>",
+    "<|ph_0065-02E9-02E9-02E6|>",
+    "<|ph_0153|>",
+    "<|ph_026A-02E7-02E9|>",
+    "<|ph_025B-02E7|>",
+    "<|ph_0061-02D0-02E6-02E5|>",
+    "<|ph_0075-0259-02E8-02E6|>",
+    "<|ph_0075-0259-02E8-02E9-02C0|>",
+    "<|ph_025B-02D0-02E8-02E9-02E8|>",
+    "<|ph_028A-02E9|>",
+    "<|ph_0062-02B2|>",
+    "<|ph_0069-0259-02E8-02E8|>",
+    "<|ph_0075-0259-02E6-02E5|>",
+    "<|ph_0061-02D0-02E8-02C0-02E5|>",
+    "<|ph_0073-0348|>",
+    "<|ph_0077-02D0|>",
+    "<|ph_0062-02B2-02D0|>",
+    "<|ph_0061-02E8-02E9-02E8|>",
+    "<|ph_026F-0061-02E9-02E9-02E6|>",
+    "<|ph_025B-02E9-02E9-02E6|>",
+    "<|ph_0061-0303|>",
+    "<|ph_0065-02D0-02E8-02E9|>",
+    "<|ph_026F-0061-02E6-02E5|>",
+    "<|ph_0074-0348-02B2|>",
+    "<|ph_0075-02E8-02E9-02E8|>",
+    "<|ph_014B-030D|>",
+    "<|ph_0075-02D0-02E8-02E9-02E8|>",
+    "<|ph_0065-006A-02E7|>",
+    "<|ph_0268-0259-02E8-02E9-02C0|>",
+    "<|ph_0074-0255|>",
+    "<|ph_0069-0259-02E8-02E9-02C0|>",
+    "<|ph_0259-02E8-02E9|>",
+    "<|ph_0065-02E8-02E9-02E8|>",
+    "<|ph_026F|>",
+    "<|ph_025B-02D0-02E8-02E6|>",
+    "<|ph_0278-02B7|>",
+    "<|ph_006F-02D0-02E8-02E9-02E8|>",
+    "<|ph_0075-02D0-02E8-02C0-02E5|>",
+    "<|ph_006E-0329-02E7-02E5|>",
+    "<|ph_025F-029D|>",
+    "<|ph_0076|>",
+    "<|ph_006F-0303|>",
+    "<|ph_0069-02E8-02E9-02E6|>",
+    "<|ph_0259-02D0-02E8-02E9-02E6|>",
+    "<|ph_0079-02E8-02E9-02E6|>",
+    "<|ph_0070-02B7|>",
+    "<|ph_0075-0259-02E8-02E9|>",
+    "<|ph_025F-02D0|>",
+    "<|ph_025B-02D0-02E5-02E9|>",
+    "<|ph_0254-02E8-02E6|>",
+    "<|ph_026A-02E5-02E7|>",
+    "<|ph_026B-02D0|>",
+    "<|ph_025B-02D0-02E5-02E7|>",
+    "<|ph_0065-02E8-02E9-02C0|>",
+    "<|ph_0274-02D0|>",
+    "<|ph_0061-0077-02E8-02E9-02E6|>",
+    "<|ph_0065|>",
+    "<|ph_0076-02B2|>",
+    "<|ph_0268-0259-02E8-02E8|>",
+    "<|ph_0074-0348|>",
+    "<|ph_0254-02D0-02E6-02E5|>",
+    "<|ph_0074-0255-02B7-02D0|>",
+    "<|ph_006E-0329|>",
+    "<|ph_00F8-02D0|>",
+    "<|ph_0254|>",
+    "<|ph_0069-02D0-02E8-02E8|>",
+    "<|ph_0075-02D0-02E6-02E5|>",
+    "<|ph_0066-02B2|>",
+    "<|ph_006F-02D0-02E8-02C0-02E5|>",
+    "<|ph_0290-02D0|>",
+    "<|ph_00E7-02D0|>",
+    "<|ph_0264-02D0-02E5-02E9|>",
+    "<|ph_006F|>",
+    "<|ph_0069-0259-02E8-02E9-02E6|>",
+    "<|ph_0069-02D0-02E8-02E9-02E6|>",
+    "<|ph_0267|>",
+    "<|ph_0259-02D0-02E8-02E8|>",
+    "<|ph_0272-02D0|>",
+    "<|ph_0268-0259-02E8-02E9|>",
+    "<|ph_014B-030D-02E7-02E5|>",
+    "<|ph_006F-02D0-02E9-02E9-02E6|>",
+    "<|ph_0261-0062|>",
+    "<|ph_0061-02E6-02E5|>",
+    "<|ph_014B-006D|>",
+    "<|ph_0283|>",
+    "<|ph_028E-02D0|>",
+    "<|ph_029D|>",
+    "<|ph_0062-02B7|>",
+    "<|ph_0074-0255-02B7|>",
+    "<|ph_0074-02B2-02D0|>",
+    "<|ph_028F-02E7-02E9|>",
+    "<|ph_0288-02B0|>",
+    "<|ph_0072-02B2-02D0|>",
+    "<|ph_0259-02E6-02E5|>",
+    "<|ph_0069-02D0-02E8-02E9-02C0|>",
+    "<|ph_0268-0259-02E8-02E9-02E8|>",
+    "<|ph_0075-02E5-02E9|>",
+    "<|ph_0077|>",
+    "<|ph_0268-02E8-02E9-02E6|>",
+    "<|ph_026F-02E5-02E9|>",
+    "<|ph_026F-02E7|>",
+    "<|ph_0069-02D0-02E7|>",
+    "<|ph_0075-02E7|>",
+    "<|ph_006D-0329|>",
+    "<|ph_026B-0329|>",
+    "<|ph_025B-02E5-02E9|>",
+    "<|ph_0289-02D0-02E7-02E9|>",
+    "<|ph_0073-032A-02D0|>",
+    "<|ph_0259-02D0-02E8-02C0-02E5|>",
+    "<|ph_0075-0061-02E7|>",
+    "<|ph_0290-0329-02E7-02E5|>",
+    "<|ph_0075-0061-02E9-02E9-02E6|>",
+    "<|ph_0062-02D0|>",
+    "<|ph_025B-02D0|>",
+    "<|ph_025D|>",
+    "<|ph_0264-02E8-02E9|>",
+    "<|ph_0074|>",
+    "<|ph_0254-02D0-02E8-02E8|>",
+    "<|ph_0069-02D0-02E8-02E9-02E8|>",
+    "<|ph_0254-02E7|>",
+    "<|ph_0065-02D0-02E9|>",
+    "<|ph_0061-006A-02E7|>",
+    "<|ph_006D|>",
+    "<|ph_0061-02E8-02E9|>",
+    "<|ph_0268-02E8-02C0-02E5|>",
+    "<|ph_00E6|>",
+    "<|ph_0074-02D0|>",
+    "<|ph_0065-02E8-02E9-02E6|>",
+    "<|ph_0073-0348-02D0|>",
+    "<|ph_0069-02E7|>",
+    "<|ph_0268-0259-02E8-02C0-02E5|>",
+    "<|ph_0079-02E5-02E9|>",
+    "<|ph_006E-032A-02D0|>",
+    "<|ph_0075-02D0-02E8-02E9-02E6|>",
+    "<|ph_0153-02E5-02E9|>",
+    "<|ph_0063-02B7|>",
+    "<|ph_0074-032A-02B0|>",
+    "<|ph_0275|>",
+    "<|ph_0063-02B0-02D0|>",
+    "<|ph_006F-02E5|>",
+    "<|ph_0075-0061-02E6-02E5|>",
+    "<|ph_0069-02D0-02E9-02E9-02E6|>",
+    "<|ph_0270|>",
+    "<|ph_0261-02B7|>",
+    "<|ph_0254-02D0-02E5-02E9|>",
+    "<|ph_028C|>",
+    "<|ph_0268|>",
+    "<|ph_026F-02D0-02E7|>",
+    "<|ph_0069-0259-02E8-02E9-02E8|>",
+    "<|ph_0074-032A-0073-032A-02D0|>",
+    "<|ph_025C|>",
+    "<|ph_0064-0291-02B7|>",
+    "<|ph_028F|>",
+    "<|ph_0257|>",
+    "<|ph_0070-0348-02B7|>",
+    "<|ph_0074-0255-0348-02B7|>",
+    "<|ph_0292|>",
+    "<|ph_03B2|>",
+    "<|ph_0063-02B0|>",
+    "<|ph_00F8-02D0-02E9|>",
+    "<|ph_0069-02E8-02E9-02C0|>",
+    "<|ph_0061-02E7|>",
+    "<|ph_0064-0292|>",
+    "<|ph_0268-02E8-02E9-02C0|>",
+    "<|ph_0263|>",
+    "<|ph_0288|>",
+    "<|ph_0283-02D0|>",
+    "<|ph_006F-02E8-02E8|>",
+    "<|ph_0061-006A-02E5-02E9|>",
+    "<|ph_0153-02E7-02E9|>",
+    "<|ph_0069-0061-02E6-02E5|>",
+    "<|ph_0294|>",
+    "<|ph_0064-02B2-02D0|>",
+    "<|ph_027E-02D0|>",
+    "<|ph_0061-006A-02E5|>",
+    "<|ph_0069-02E8-02E6|>",
+    "<|ph_028C-02D0|>",
+    "<|ph_0252|>",
+    "<|ph_0065-02D0-02E8-02E6|>",
+    "<|ph_0278-02D0|>",
+    "<|ph_006F-0077-02E8-02E9-02E6|>",
+    "<|ph_0266|>",
+    "<|ph_0069-02E5|>",
+    "<|ph_0254-02E9|>",
+    "<|ph_0065-006A-02E8-02E9-02E6|>",
+    "<|ph_0074-02B0|>",
+    "<|ph_0264-02E9-02E9-02E6|>",
+    "<|ph_006E-0329-02E8-02E9-02E6|>",
+    "<|ph_0064-0291-02D0|>",
+    "<|ph_0255|>",
+    "<|ph_0064-02D0|>",
+    "<|ph_0259-02D0-02E6-02E5|>",
+    "<|ph_007A-0329-02E5|>",
+    "<|ph_0075-02E7-02E5|>",
+    "<|ph_0079-02E7-02E5|>",
+    "<|ph_0075-0259-02E8-02C0-02E5|>",
+    "<|ph_0254-02E8-02E9-02C0|>",
+    "<|ph_0075-02D0-02E5-02E7|>",
+    "<|ph_0069-0061-02E9-02E9-02E6|>",
+    "<|ph_006F-02D0-02E7-02E9|>",
+    "<|ph_0268-02E8-02E6|>",
+    "<|ph_006F-02D0-02E8-02E9-02C0|>",
+    "<|ph_006F-02D0-02E5-02E7|>",
+    "<|ph_0061-02E8-02E9-02C0|>",
+    "<|ph_0254-02D0-02E8-02C0-02E5|>",
+    "<|ph_0061-02D0-02E7|>",
+    "<|ph_0268-0259-02E8-02E6|>",
+    "<|ph_0064-007A-02B2-02D0|>",
+    "<|ph_0069-02E8-02E9-02E8|>",
+    "<|ph_0076-02B2-02D0|>",
+    "<|ph_0065-02D0|>",
+    "<|ph_0290-0329-02E8-02E9-02E6|>",
+    "<|ph_006E-02D0|>",
+    "<|ph_0075-0259-02E8-02E9-02E6|>",
+    "<|ph_0073-02B7|>",
+    "<|ph_007A-0329-02E5-02E9|>",
+    "<|ph_0075-02D0|>",
+    "<|ph_0074-0283-02D0|>",
+    "<|ph_0288-0282-02B0|>",
+    "<|ph_026A-02E5-02E9|>",
+    "<|ph_014B|>",
+    "<|ph_0079-02E7|>",
+    "<|ph_006B-02B0|>",
+    "<|ph_0069-02E5-02E9|>",
+    "<|ph_0259-02E8-02E8|>",
+    "<|ph_0070-0348-02D0|>",
+    "<|ph_0274|>",
+    "<|ph_0061-02D0-02E8-02E8|>",
+    "<|ph_0070-0348|>",
+    "<|ph_0259-02D0-02E8-02E9-02E8|>",
+    "<|ph_006F-02E8-02E9-02E8|>",
+    "<|ph_006B-02B7|>",
+    "<|ph_007A-02B2|>",
+    "<|ph_0074-02B7-02D0|>",
+    "<|ph_00F8|>",
+    "<|ph_026A-02E9|>",
+    "<|ph_0074-0255-02B0|>",
+    "<|ph_0251-0303|>",
+    "<|ph_0074-0348-02D0|>",
+    "<|ph_0259-02E7-02E5|>",
+    "<|ph_006B-02B7-02D0|>",
+    "<|ph_0074-032A-0073-032A|>",
+    "<|ph_0268-02D0-02E6-02E5|>",
+    "<|ph_0061|>",
+    "<|ph_0069-02E7-02E5|>",
+    "<|ph_0078-02D0|>",
+    "<|ph_0075-02E8-02E9|>",
+    "<|ph_0070-02B2|>",
+    "<|ph_0271|>",
+    "<|ph_0075-0259-02E8-02E8|>",
+    "<|ph_006F-02E8-02E6|>",
+    "<|ph_0075-02E5|>",
+    "<|ph_0290-0329-02E9|>",
+    "<|ph_0068-02D0|>",
+    "<|ph_0259-02E5-02E9|>",
+    "<|ph_0075-02E8-02E9-02C0|>",
+    "<|ph_0065-006A-02E9|>",
+    "<|ph_0069-0061-02E8-02E9|>",
+    "<|ph_006C-032A|>",
+    "<|ph_0069-02E6-02E5|>",
+    "<|ph_0074-0282-02D0|>",
+    "<|ph_006F-02E9|>",
+    "<|ph_03B2-02B7|>",
+    "<|ph_0268-0325|>",
+    "<|ph_0278-02B2-02D0|>",
+    "<|ph_0064-007A-02D0|>",
+    "<|ph_0268-02D0-02E8-02E9|>",
+    "<|ph_0074-0073-02B0|>",
+    "<|ph_006D-0329-02E8-02E9-02E6|>",
+    "<|ph_0079-02D0-02E9|>",
+    "<|ph_0074-02B2|>",
+    "<|ph_0259-02E8-02E9-02E8|>",
+    "<|ph_0061-0077|>",
+    "<|ph_0069-0061-02E7|>",
+    "<|ph_0074-0073-02D0|>",
+    "<|ph_006A-0303|>",
+    "<|ph_0064-02B7|>",
+    "<|ph_007A-032A-02D0|>",
+    "<|ph_0254-02D0-02E8-02E9-02C0|>",
+    "<|ph_0259-02E8-02E9-02C0|>",
+    "<|ph_006F-02D0-02E8-02E9|>",
+    "<|ph_0251|>",
+    "<|ph_0065-02D0-02E5-02E9|>",
+    "<|ph_0066-02D0|>",
+    "<|ph_0065-02D0-02E8-02E9-02C0|>",
+    "<|ph_0069-02D0-02E5-02E9|>",
+    "<|ph_0268-02D0-02E8-02E8|>",
+    "<|ph_026F-02D0-02E9-02E9-02E6|>",
+    "<|ph_0061-02E9|>",
+    "<|ph_007A-0329-02E9|>",
+    "<|ph_0272|>",
+    "<|ph_026A|>",
+    "<|ph_0075-02E8-02C0-02E5|>",
+    "<|ph_0061-02E8-02E6|>",
+    "<|ph_0066-02B7|>",
+    "<|ph_0065-02D0-02E9-02E9-02E6|>",
+    "<|ph_0259-02D0-02E8-02E6|>",
+    "<|ph_0291-02D0|>",
+    "<|ph_0259-02E8-02C0-02E5|>",
+    "<|ph_0065-006A-02E5|>",
+    "<|ph_006D-02D0|>",
+    "<|ph_0254-02E7-02E9|>",
+    "<|ph_0069-02E8-02C0-02E5|>",
+    "<|ph_0254-02E6-02E5|>",
+    "<|ph_027E-0303|>",
+    "<|ph_0061-006A-02E7-02E5|>",
+    "<|ph_0079-02D0-02E5-02E9|>",
+    "<|ph_026D|>",
+    "<|ph_0289-02D0|>",
+    "<|ph_0075-02E8-02E8|>",
+    "<|ph_025B-02D0-02E9-02E9-02E6|>",
+    "<|ph_0264-02D0-02E7|>",
+    "<|ph_006F-02D0-02E8-02E9-02E6|>",
+    "<|ph_014B-030D-02E5-02E9|>",
+    "<|ph_0254-028F|>",
+    "<|ph_006B-02B0-02D0|>",
+    "<|ph_025B-02E5-02E7|>",
+    "<|ph_025B-02E7-02E9|>",
+    "<|ph_0075-0259-02E8-02E9-02E8|>",
+    "<|ph_0061-006A-02E8-02E9-02E6|>",
+    "<|ph_0069-0259-02E6-02E5|>",
+    "<|ph_0069-0303|>",
+    "<|ph_025B-02D0-02E8-02E9|>",
+    "<|ph_025B|>",
+    "<|ph_0264-02E5-02E9|>",
+    "<|ph_026B|>",
+    "<|ph_0264-02E7|>",
+    "<|ph_0268-02E8-02E8|>",
+    "<|ph_0068|>",
+    "<|ph_028B|>",
+    "<|ph_0065-02E5-02E9|>",
+    "<|ph_0254-02E8-02E9-02E6|>",
+    "<|ph_0264-02D0-02E8-02E9|>",
+    "<|ph_0073-0069-006C|>",
+    "<|ph_0069-02D0-02E6-02E5|>",
+    "<|ph_0061-02D0-02E5-02E9|>",
+    "<|ph_025B-02D0-02E6-02E5|>",
+    "<|ph_027E-02B7|>",
+    "<|ph_0073-02B0-02D0|>",
+    "<|ph_025B-0303|>",
+    "<|ph_006F-02D0-02E5-02E9|>",
+    "<|ph_0254-02E8-02E9|>",
+    "<|ph_006E-032A|>",
+    "<|ph_006A|>",
+    "<|ph_0264-02D0-02E6-02E5|>",
+    "<|ph_0070-02D0|>",
+    "<|ph_0065-02D0-02E6-02E5|>",
+    "<|ph_0254-02E9-02E9-02E6|>",
+    "<|ph_00F0|>",
+    "<|ph_0253|>",
+    "<|ph_0275-02E7-02E9|>",
+    "<|ph_0064-032A|>",
+    "<|ph_0073-02B2|>",
+    "<|ph_0290-0329-02E5|>",
+    "<|ph_025B-02D0-02E8-02E9-02C0|>",
+    "<|ph_0063|>",
+    "<|ph_006E|>",
+    "<|ph_006F-0077-02E9|>",
+    "<|ph_0079-02D0-02E5-02E7|>",
+    "<|ph_0070|>",
+    "<|ph_028F-02E5-02E7|>",
+    "<|ph_0075-02E6-02E5|>",
+    "<|ph_0073-02B0|>",
+    "<|ph_006F-02D0-02E7|>",
+    "<|ph_0069-02D0|>",
+    "<|ph_0268-0259-02E6-02E5|>",
+    "<|ph_0061-02D0|>",
+    "<|ph_0075-02D0-02E7|>",
+    "<|ph_006B-0348-02B7|>",
+    "<|ph_0070-02B0-02D0|>",
+    "<|ph_0065-02E6-02E5|>",
+    "<|ph_0069-0325|>",
+    "<|ph_0066|>",
+    "<|ph_0075|>",
+    "<|ph_0069-02E9-02E9-02E6|>",
+    "<|ph_0062|>",
+    "<|ph_0063-02D0|>",
+    "<|ph_0273|>",
+    "<|ph_0254-02D0-02E8-02E9|>",
+    "<|ph_0065-02D0-02E5-02E7|>",
+    "<|ph_03B8|>",
+    "<|ph_0061-006A-02E9|>",
+    "<|ph_0061-02E7-02E9|>",
+    "<|ph_0069-02D0-02E8-02E6|>",
+    "<|ph_006D-0329-02E5-02E9|>",
+    "<|ph_026F-02D0-02E8-02E9|>",
+    "<|ph_0075-02D0-02E5-02E9|>",
+    "<|ph_0291|>",
+    "<|ph_0065-02E7-02E5|>",
+    "<|ph_0268-02D0-02E8-02E9-02C0|>",
+    "<|ph_0061-02E5-02E9|>",
+    "<|ph_028A-02E7-02E9|>",
+    "<|ph_0268-02E8-02E9-02E8|>",
+    "<|ph_026F-02E8-02E9|>",
+    "<|ph_0259-02E7|>",
+    "<|ph_0061-02E7-02E5|>",
+    "<|ph_0065-02E8-02E9|>",
+    "<|ph_0069-0259-02E8-02E9|>",
+    "<|ph_006F-02E8-02E9|>",
+    "<|ph_0061-02E8-02E8|>",
+    "<|ph_006F-0077-02E5-02E9|>",
+    "<|ph_0075-02D0-02E7-02E9|>",
+    "<|ph_0065-0303|>",
+    "<|ph_0254-02E8-02C0-02E5|>",
+    "<|ph_0268-02E8-02E9|>",
+    "<|ph_006D-0329-02E7-02E5|>",
+    "<|ph_006E-0329-02E5-02E9|>",
+    "<|ph_0290-0329-02E7|>",
+    "<|ph_0075-02E9|>",
+    "<|ph_006F-0077|>",
+    "<|ph_0290-0329-02E5-02E9|>",
+    "<|ph_0254-0303|>",
+    "<|ph_0254-02E8-02E8|>",
+    "<|ph_006B-0348|>",
+    "<|ph_0079-02D0|>",
+    "<|ph_0250|>",
+    "<|ph_0075-02D0-02E8-02E6|>",
+    "<|ph_026F-0061-02E5-02E9|>",
+    "<|ph_025B-02E6-02E5|>",
+    "<|ph_0074-0255-02B0-02D0|>",
+    "<|ph_0075-0061-02E5-02E9|>",
+    "<|ph_0064-0290|>",
+    "<|ph_0259-02E8-02E6|>",
+    "<|ph_0281|>",
+    "<|ph_0061-02D0-02E9-02E9-02E6|>",
+    "<|ph_0256|>",
+    "<|ph_0288-02B7|>",
+    "<|ph_025B-02D0-02E8-02E9-02E6|>",
+    "<|ph_0070-02B0|>",
+    "<|ph_0254-006A|>",
+    "<|ph_026D-02D0|>",
+    "<|ph_006F-02E5-02E9|>",
+    "<|ph_0061-0077-02E7|>",
+    "<|ph_0074-0282|>",
+    "<|ph_0255-02B0|>",
+    "<|ph_006B-0070|>",
+    "<|ph_0251-02D0-02E7-02E9|>",
+    "<|ph_026F-0061-02E8-02E9|>",
+    "<|ph_014B-030D-02E8-02E9-02E6|>",
+    "<|ph_0061-02E8-02E9-02E6|>",
+    "<|ph_0073-032A|>",
+    "<|ph_0065-02E7|>",
+    "<|ph_0079-02D0-02E7-02E9|>",
+    "<|ph_006F-02D0-02E6-02E5|>",
+    "<|ph_0074-02B0-02D0|>",
+    "<|ph_0251-02D0-02E5-02E7|>",
+    "<|ph_0259|>",
+    "<|ph_0061-02E5|>",
+    "<|ph_0278|>",
+    "<|ph_0268-02D0-02E8-02E6|>",
+    "<|ph_027E|>",
+    "<|ph_027E-02B2-02D0|>",
+    "<|ph_006F-02D0-02E9|>",
+    "<|ph_0268-02D0-02E8-02E9-02E6|>",
+    "<|ph_006F-02E8-02E9-02C0|>",
+    "<|ph_006D-02B2-02D0|>",
+    "<|ph_0289-02D0-02E5-02E9|>",
+    "<|ph_0074-0255-0348|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29da3b5cfb25e3d531cc3e07fd5b22d40cf644e5df9f99307c467b59bf825a9a
+size 29650442

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77d48da4cbf813726cb90cc11fa675afeec3b90649b32834c1b3eb68ce4f639
+size 11847842