Featherless
DynaGuard-1.7BTomg group umd
Start Chat
2B Params BF16 Open Weights Inference Available

DynaGuard-1.7B is a 1.7 billion parameter decoder-only Transformer model developed by the University of Maryland and Capital One, based on Qwen3-1.7B. This guardian model evaluates text against user-defined natural language policies, offering a flexible solution for moderating chatbot outputs beyond static harm categories. It excels at enforcing bespoke, application-specific rules and provides both fast inference and interpretable Chain-of-Thought reasoning modes. DynaGuard-1.7B achieves strong performance on safety and compliance benchmarks, making it suitable for dynamic content moderation.

Loading preview...

Parameters:2BContext length:32kArchitecture:TransformerPrecision:BF16Quantized variants:AvailableLast updated:July 2025
0.0M
0.0K

Model tree for

tomg-group-umd/DynaGuard-1.7B
Popular Sampler Settings

Most commonly used values from Featherless users

temperature

This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.

top_p

This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.

top_k

This limits the number of top tokens to consider. Set to -1 to consider all tokens.

frequency_penalty

This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.

presence_penalty

This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.

repetition_penalty

This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.

min_p

This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.