WaltonFuture/Diabetica-7B
Diabetica-7B by WaltonFuture is a 7.6 billion parameter specialized large language model designed for diabetes care and management, featuring a context length of 131072 tokens. It excels across a broad range of diabetes-related tasks, including diagnosis, treatment recommendations, medication management, and patient education. This model offers superior performance in domain-specific medical tasks compared to generic LLMs, developed through a reproducible framework using curated disease-specific datasets and fine-tuning techniques. It is intended for accelerating AI-assisted care development in diabetes and other medical fields.
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.
–