sam-paech/Quill-v1
TEXT GENERATIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:16kPublished:Oct 20, 2024Architecture:Transformer0.0K Warm

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...