tomg-group-umd/DynaGuard-8B
DynaGuard-8B is an 8 billion parameter decoder-only Transformer model developed by the University of Maryland and Capital One, based on Qwen3-8B. It is fine-tuned for evaluating text against user-defined natural language policies, functioning as a dynamic guardrail model. This model excels at moderating chatbot outputs with bespoke rules and provides interpretability through detailed explanations for policy violations. DynaGuard-8B achieves state-of-the-art performance on safety and compliance benchmarks, outperforming generalist models like GPT-4o-mini.
Hugging Face 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.
–