The Rhea project is a project that conducts research on various learning methods to improve llm model performance. We fine-tuned the existing model using the
nox
framework. We built a dataset for SFT learning based on the currently open dataset, and created a dataset using SGD (Self-Generated Dataset Creation Method for DPO Learning) for DPO learning.
Our model ranked first on HuggingFace's Open LLM leaderboard.
SGD : A Study on Self-Generated Dataset creation method for DPO Learning
This method proposes a novel method for generating datasets for DPO (Self-supervised Learning) models. We suggest a technique where sentences generated by the model are compared with the actual correct answers from an existing dataset, and sentences where the model's generated results do not match the correct answers are added. This enables the model to autonomously create training data, thereby enhancing the performance of DPO models.
Rhea-72b-v0.5-bpw5.5 huggingface.co is an AI model on huggingface.co that provides Rhea-72b-v0.5-bpw5.5's model effect (), which can be used instantly with this blockblockblock Rhea-72b-v0.5-bpw5.5 model. huggingface.co supports a free trial of the Rhea-72b-v0.5-bpw5.5 model, and also provides paid use of the Rhea-72b-v0.5-bpw5.5. Support call Rhea-72b-v0.5-bpw5.5 model through api, including Node.js, Python, http.
Rhea-72b-v0.5-bpw5.5 huggingface.co is an online trial and call api platform, which integrates Rhea-72b-v0.5-bpw5.5's modeling effects, including api services, and provides a free online trial of Rhea-72b-v0.5-bpw5.5, you can try Rhea-72b-v0.5-bpw5.5 online for free by clicking the link below.
blockblockblock Rhea-72b-v0.5-bpw5.5 online free url in huggingface.co:
Rhea-72b-v0.5-bpw5.5 is an open source model from GitHub that offers a free installation service, and any user can find Rhea-72b-v0.5-bpw5.5 on GitHub to install. At the same time, huggingface.co provides the effect of Rhea-72b-v0.5-bpw5.5 install, users can directly use Rhea-72b-v0.5-bpw5.5 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Rhea-72b-v0.5-bpw5.5 install url in huggingface.co: