nvidia/Qwen3-Nemotron-14B-BRRM
The nvidia/Qwen3-Nemotron-14B-BRRM is a 14 billion parameter Branch-and-Rethink Reasoning Reward Model developed by NVIDIA. This model implements a novel two-turn reasoning framework for evaluating LLM-generated responses, performing adaptive branching and branch-conditioned rethinking to focus on critical evaluation dimensions. It achieves state-of-the-art performance on major reward modeling benchmarks, making it suitable for integrating into RLHF pipelines to improve LLM response quality.
Cold
Public
14B
FP8
32768
License: nvidia-internal-scientific-research-and-development-model-license
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.
–