This is a fixed version of
Eurus-70b-nca
made by copying the json files from the (
base
)
CodeLlama-70b-hf
model and adding in the Mistral chat template, eg:
<s>[INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
This version has the same context length (16k) and RoPE base frequency (1000000) as
CodeLlama-70b
:
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}
}
Runs of jukofyork Eurus-70b-nca-fixed on huggingface.co
17
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About Eurus-70b-nca-fixed huggingface.co Model
Eurus-70b-nca-fixed huggingface.co is an AI model on huggingface.co that provides Eurus-70b-nca-fixed's model effect (), which can be used instantly with this jukofyork Eurus-70b-nca-fixed model. huggingface.co supports a free trial of the Eurus-70b-nca-fixed model, and also provides paid use of the Eurus-70b-nca-fixed. Support call Eurus-70b-nca-fixed model through api, including Node.js, Python, http.
Eurus-70b-nca-fixed huggingface.co is an online trial and call api platform, which integrates Eurus-70b-nca-fixed's modeling effects, including api services, and provides a free online trial of Eurus-70b-nca-fixed, you can try Eurus-70b-nca-fixed online for free by clicking the link below.
jukofyork Eurus-70b-nca-fixed online free url in huggingface.co:
Eurus-70b-nca-fixed is an open source model from GitHub that offers a free installation service, and any user can find Eurus-70b-nca-fixed on GitHub to install. At the same time, huggingface.co provides the effect of Eurus-70b-nca-fixed install, users can directly use Eurus-70b-nca-fixed installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Eurus-70b-nca-fixed install url in huggingface.co: