Quill-v1 by sam-paech is a 9 billion parameter language model based on Gemma-2-9b-it, fine-tuned for human-like writing with a natural cadence and low "gpt-slop." It was trained using ORPO and SIMPO methods on the Gutenberg3 dataset, which comprises late 19th and early 20th-century fiction. This model excels at generating prose with a simple, spare style, achieving a score of 79.75 on the EQ-Bench creative writing benchmark, making it ideal for creative writing tasks requiring a classic literary tone.
Loading preview...
Model tree for
sam-paech/Quill-v1Most 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.