RichardErkhov/openbmb_-_Eurus-7b-kto-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Eurus-7b-kto - GGUF

• Model creator: https://huggingface.co/openbmb/
• Original model: https://huggingface.co/openbmb/Eurus-7b-kto/

Name	Quant method	Size
Eurus-7b-kto.Q2_K.gguf	Q2_K	2.53GB
Eurus-7b-kto.IQ3_XS.gguf	IQ3_XS	2.81GB
Eurus-7b-kto.IQ3_S.gguf	IQ3_S	2.96GB
Eurus-7b-kto.Q3_K_S.gguf	Q3_K_S	2.95GB
Eurus-7b-kto.IQ3_M.gguf	IQ3_M	3.06GB
Eurus-7b-kto.Q3_K.gguf	Q3_K	3.28GB
Eurus-7b-kto.Q3_K_M.gguf	Q3_K_M	3.28GB
Eurus-7b-kto.Q3_K_L.gguf	Q3_K_L	3.56GB
Eurus-7b-kto.IQ4_XS.gguf	IQ4_XS	3.67GB
Eurus-7b-kto.Q4_0.gguf	Q4_0	3.83GB
Eurus-7b-kto.IQ4_NL.gguf	IQ4_NL	3.87GB
Eurus-7b-kto.Q4_K_S.gguf	Q4_K_S	3.86GB
Eurus-7b-kto.Q4_K.gguf	Q4_K	4.07GB
Eurus-7b-kto.Q4_K_M.gguf	Q4_K_M	4.07GB
Eurus-7b-kto.Q4_1.gguf	Q4_1	4.24GB
Eurus-7b-kto.Q5_0.gguf	Q5_0	4.65GB
Eurus-7b-kto.Q5_K_S.gguf	Q5_K_S	4.65GB
Eurus-7b-kto.Q5_K.gguf	Q5_K	4.78GB
Eurus-7b-kto.Q5_K_M.gguf	Q5_K_M	4.78GB
Eurus-7b-kto.Q5_1.gguf	Q5_1	5.07GB
Eurus-7b-kto.Q6_K.gguf	Q6_K	5.53GB
Eurus-7b-kto.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 datasets: - openbmb/UltraFeedback - openbmb/UltraInteract_pair tags: - reasoning - preference_learning - kto pipeline_tag: text-generation

Eurus: A suit of open-source LLMs optimized for reasoning

Introduction • Evaluation

Links

• 📜 Paper
• 🤗 Eurus Collection
• 🤗 UltraInteract
  • SFT
  • Preference Learning
• GitHub Repo

Introduction

Eurus-7B-KTO is KTO fine-tuned from Eurus-7B-SFT on all multi-turn trajectory pairs in UltraInteract and all pairs in UltraFeedback.

It achieves the best overall performance among open-source models of similar sizes and even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B-KTO outperforms baselines that are 5× larger.

Usage

We apply tailored prompts for coding and math, consistent with UltraInteract data formats:

Coding

[INST] Write Python code to solve the task:
{Instruction} [/INST]

Math-CoT

[INST] Solve the following math problem step-by-step.
Simplify your answer as much as possible. Present your final answer as \\boxed{Your Answer}.
{Instruction} [/INST]

Math-PoT

[INST] Tool available:
[1] Python interpreter
When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment.
Solve the following math problem step-by-step.
Simplify your answer as much as possible.
{Instruction} [/INST]

Evaluation

• Eurus, both the 7B and 70B variants, achieve the best overall performance among open-source models of similar sizes. Eurus even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B outperforms baselines that are 5× larger, and Eurus-70B achieves better performance than GPT-3.5 Turbo.
• Preference learning with UltraInteract can further improve performance, especially in math and the multi-turn ability.

Citation

@misc{yuan2024advancing,
      title={Advancing LLM Reasoning Generalists with Preference Trees}, 
      author={Lifan Yuan and Ganqu Cui and Hanbin Wang and Ning Ding and Xingyao Wang and Jia Deng and Boji Shan and Huimin Chen and Ruobing Xie and Yankai Lin and Zhenghao Liu and Bowen Zhou and Hao Peng and Zhiyuan Liu and Maosong Sun},
      year={2024},
      eprint={2404.02078},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}