Smaug-Mixtral-v0.1

Model overview

This model is part of the Smaug series of finetuned models. This one based on https://huggingface.co/mistralai/Mixtral-8x7B-v0.1 We use a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228. We show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases. Using these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode. Surprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.

Key features

特点摘要待依据来源补齐，不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

Frequently asked questions

Sources & traceability

许可证：apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。