snuh/hari-q2.5-thinking
The snuh/hari-q2.5-thinking model is a Korean Medical Large Language Model (LLM) developed by the Healthcare AI Research Institute (HARI) at Seoul National University Hospital (SNUH). This model is fine-tuned on Korean medical question-answering (QA) style data, enabling robust performance in clinical reasoning and medical education. It achieves 89.2% accuracy on the Korean Medical Licensing Examination (KMLE) and 88.36% on the USMLE QA benchmark, making it suitable for clinical decision support and medical self-assessment tools.
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.
โ
top_p
This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.
โ
top_k
This limits the number of top tokens to consider. Set to -1 to consider all tokens.
โ
frequency_penalty
This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.
โ
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.
โ
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.
โ
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.
โ