argilla/distilabeled-Marcoro14-7B-slerp
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jan 11, 2024License:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Cold

The argilla/distilabeled-Marcoro14-7B-slerp model is a 7 billion parameter DPO fine-tune by Argilla, built upon the mlabonne/Marcoro14-7B-slerp base model. It leverages a refined version of the Intel Orca DPO dataset, specifically filtered for high-quality pairs. This model demonstrates improved performance on benchmarks like AGIEval and TruthfulQA compared to its base, making it suitable for general-purpose conversational AI and reasoning tasks.

Loading preview...