Quantization made by Richard Erkhov.

Eurus-70b-nca - GGUF

Model creator: https://huggingface.co/openbmb/
Original model: https://huggingface.co/openbmb/Eurus-70b-nca/

Name	Quant method	Size
Eurus-70b-nca.Q2_K.gguf	Q2_K	23.71GB
Eurus-70b-nca.IQ3_XS.gguf	IQ3_XS	26.37GB
Eurus-70b-nca.IQ3_S.gguf	IQ3_S	27.86GB
Eurus-70b-nca.Q3_K_S.gguf	Q3_K_S	27.86GB
Eurus-70b-nca.IQ3_M.gguf	IQ3_M	28.82GB
Eurus-70b-nca.Q3_K.gguf	Q3_K	30.99GB
Eurus-70b-nca.Q3_K_M.gguf	Q3_K_M	30.99GB
Eurus-70b-nca.Q3_K_L.gguf	Q3_K_L	33.67GB
Eurus-70b-nca.IQ4_XS.gguf	IQ4_XS	34.64GB
Eurus-70b-nca.Q4_0.gguf	Q4_0	36.2GB
Eurus-70b-nca.IQ4_NL.gguf	IQ4_NL	36.55GB
Eurus-70b-nca.Q4_K_S.gguf	Q4_K_S	36.55GB
Eurus-70b-nca.Q4_K.gguf	Q4_K	38.58GB
Eurus-70b-nca.Q4_K_M.gguf	Q4_K_M	38.58GB
Eurus-70b-nca.Q4_1.gguf	Q4_1	40.2GB
Eurus-70b-nca.Q5_0.gguf	Q5_0	44.2GB
Eurus-70b-nca.Q5_K_S.gguf	Q5_K_S	44.2GB
Eurus-70b-nca.Q5_K.gguf	Q5_K	33.46GB
Eurus-70b-nca.Q5_K_M.gguf	Q5_K_M	45.41GB
Eurus-70b-nca.Q5_1.gguf	Q5_1	48.2GB
Eurus-70b-nca.Q6_K.gguf	Q6_K	52.7GB
Eurus-70b-nca.Q8_0.gguf	Q8_0	68.26GB

Original model description:

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

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

Introduction • Evaluation

Introduction

Eurus-70B-NCA is NCA fine-tuned from Eurus-70B-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-70B-NCA achieves better performance than GPT-3.5 Turbo through comprehensive benchmarking across 12 tests covering five tasks.

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}
}

RichardErkhov
/

openbmb_-_Eurus-70b-nca-gguf