Intended Use

Primary Use Cases

Out-of-Scope Use Cases

Responsible AI Considerations

• Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups, cultural contexts, or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.
• Inappropriate or Offensive Content: These models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.
• Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.
• Limited Scope for Code: Majority of Domyn Large training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.
• Long Conversation: Domyn Large, like other models, can in some cases generate responses that are repetitive, unhelpful, or inconsistent in very long chat sessions in both English and non-English languages. Developers are encouraged to place appropriate mitigations, like limiting conversation turns to account for the possible conversational drift.

• Audit & Monitoring: Use third-party safety tools (e.g., Azure AI Content Safety) to detect and filter harmful or unsafe outputs.
• Transparency: Clearly inform users when they are interacting with an AI system, and incorporate feedback loops for continual improvement.
• RAG Integration: Improve factuality and domain relevance through Retrieval-Augmented Generation (RAG).
• Immutable Logging: For sovereign or customized use, embed audit logging at the architectural level to ensure traceability and prevent tampering.
• High-Stakes Applications: Avoid deploying the model in sensitive scenarios (e.g., healthcare, legal advice, credit scoring) without extensive validation and safeguards.

Training Data

• Safety datasets designed to teach the model to provide safe, aligned responses and avoid harmful or inappropriate content.
• Long-context datasets that leverage the model's ability to handle long inputs, including long-form Q&A and document summarization tasks.
• Chat datasets to improve natural and coherent dialogue.
• Instruction-following datasets focused on explicit task instructions.
• Multilingual datasets in multiple languages to strengthen multilingual capabilities.
• Code datasets containing source code to improve programming and code reasoning skills, including structured query languages such as SQL and Cypher used for enterprise data access.
• Math datasets with mathematical problems and solutions to enhance problem-solving abilities.
• Function-calling datasets that teach the model when and how to use external tools and APIs.
• STEM datasets centered on science, technology, engineering, and mathematics topics.

• Helpfulness (instruction clarity, completeness of response)
• Complexity (depth of reasoning, cognitive load)
• Contamination (data leakage with respect to benchmark evaluations)

Reasoning Control

• Use '"thinking on"' in the system prompt to enable reasoning mode.
• Use '"thinking off"' to disable reasoning mode.

Example Usage

Enable Reasoning Mode

[
    { "role": "system", "content": "My system prompt.\n\nthinking on" },
    { "role": "user", "content": "My question" }
]

Disable Reasoning Mode

[
    { "role": "system", "content": "My system prompt.\n\nthinking off" },
    { "role": "user", "content": "My question" }
]

Default Reasoning Mode

[
    { "role": "system", "content": "My system prompt" },
    { "role": "user", "content": "My question" }
]

Tool Calling

1. Defining Tools

You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags.
You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.
Here are the available tools:
<tools>
[{'type': 'function', 'function': {'name': 'create_calendar_event', 'description': 'Create a new event in the calendar', 'parameters': {'type': 'object', 'properties': {'event_title': {'type': 'string', 'description': 'The title of the event'}, 'event_date': {'type': 'string', 'description': 'The date of the event'}, 'event_location': {'type': 'string', 'description': 'The location of the event'}}, 'required': ['event_title', 'event_date']}}}, {'type': 'function', 'function': {'name': 'convert_currency', 'description': 'Convert currency from one unit to another', 'parameters': {'type': 'object', 'properties': {'amount': {'type': 'number', 'description': 'The amount to be converted'}, 'from_currency': {'type': 'string', 'description': 'The currency to convert from'}, 'to_currency': {'type': 'string', 'description': 'The currency to convert to'}}, 'required': ['amount', 'from_currency', 'to_currency']}}}]
</tools>
For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{'arguments': <args-dict>, 'name': <function-name>}
</tool_call>

2. Representing Tool Calls and Tool Responses

• Must appear as an assistant message.
• Must be wrapped in <tool_call> and </tool_call> tags.
• Must contain a JSON object with "name" and "arguments".

• Must appear as a user message.
• Must be wrapped in <tool_response> and </tool_response> tags.
• Should contain the raw result returned by the tool.

[
  {
    "role": "system",
    "content": "You are a function-calling AI model. Here are the available tools..."
  },
  {
    "role": "user",
    "content": "Can you find Italian restaurants in New York?"
  },
  {
    "role": "assistant",
    "content": "<tool_call>{\"name\": \"find_nearby_restaurants\", \"arguments\": {\"location\": \"New York\", \"cuisine\": \"Italian\", \"radius\": 5000}}</tool_call>"
  },
  {
    "role": "user",
    "content": "<tool_response>[{\"name\": \"Da Pippo\", \"stars\": 5, \"address\": \"Central Park\"}]</tool_response>"
  }
]

Point of Contact for Copyright-Related Complaints