Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Jinja] GPT4All-Chat 3.5.1 breaks bartowski/Mistral-Nemo-Instruct-2407-GGUF #3284

Open
ThiloteE opened this issue Dec 13, 2024 · 1 comment
Labels

Comments

@ThiloteE
Copy link
Collaborator

Bug Report

Model does not work

Steps to Reproduce

  1. Download and sideload model
  2. Check model settings: Image

Here is the default non-working jinja template:

{%- if messages[0]["role"] == "system" %}
    {%- set system_message = messages[0]["content"] %}
    {%- set loop_messages = messages[1:] %}
{%- else %}
    {%- set loop_messages = messages %}
{%- endif %}
{%- if not tools is defined %}
    {%- set tools = none %}
{%- endif %}
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}

{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
{%- set ns = namespace() %}
{%- set ns.index = 0 %}
{%- for message in loop_messages %}
    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
        {%- endif %}
        {%- set ns.index = ns.index + 1 %}
    {%- endif %}
{%- endfor %}

{{- bos_token }}
{%- for message in loop_messages %}
    {%- if message["role"] == "user" %}
        {%- if tools is not none and (message == user_messages[-1]) %}
            {{- "[AVAILABLE_TOOLS][" }}
            {%- for tool in tools %}
                {%- set tool = tool.function %}
                {{- '{"type": "function", "function": {' }}
                {%- for key, val in tool.items() if key != "return" %}
                    {%- if val is string %}
                        {{- '"' + key + '": "' + val + '"' }}
                    {%- else %}
                        {{- '"' + key + '": ' + val|tojson }}
                    {%- endif %}
                    {%- if not loop.last %}
                        {{- ", " }}
                    {%- endif %}
                {%- endfor %}
                {{- "}}" }}
                {%- if not loop.last %}
                    {{- ", " }}
                {%- else %}
                    {{- "]" }}
                {%- endif %}
            {%- endfor %}
            {{- "[/AVAILABLE_TOOLS]" }}
            {%- endif %}
        {%- if loop.last and system_message is defined %}
            {{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
        {%- else %}
            {{- "[INST]" + message["content"] + "[/INST]" }}
        {%- endif %}
    {%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
        {{- "[TOOL_CALLS][" }}
        {%- for tool_call in message.tool_calls %}
            {%- set out = tool_call.function|tojson %}
            {{- out[:-1] }}
            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
            {%- endif %}
            {{- ', "id": "' + tool_call.id + '"}' }}
            {%- if not loop.last %}
                {{- ", " }}
            {%- else %}
                {{- "]" + eos_token }}
            {%- endif %}
        {%- endfor %}
    {%- elif message["role"] == "assistant" %}
        {{- message["content"] + eos_token}}
    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
        {%- if message.content is defined and message.content.content is defined %}
            {%- set content = message.content.content %}
        {%- else %}
            {%- set content = message.content %}
        {%- endif %}
        {{- '[TOOL_RESULTS]{"content": ' + content|string + ", " }}
        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
        {%- endif %}
        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
    {%- else %}
        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
    {%- endif %}
{%- endfor %}

I don't know how to fix it.

Expected Behavior

Model just works

Your Environment

@ThiloteE ThiloteE added bug-unconfirmed chat gpt4all-chat issues labels Dec 13, 2024
@ThiloteE
Copy link
Collaborator Author

ThiloteE commented Dec 13, 2024

There have been fixes to various versions of the mistral chat templates in llama.cpp. See this PR: ggerganov/llama.cpp#10572. I think GPT4All still old version of llama.cpp

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

1 participant