tulu-3-IF-augmented-on-policy-70b

<img src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/tulu-3/Tulu3-logo.png" alt="Tulu3 banner" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

# Llama 3.1 Tulu 3 IF-Augmented (on-policy 70B)

*Note that this collection is licensed under ODC-BY-1.0 license; different licenses apply to subsets of the data. Some portions of the dataset are non-commercial. We present the mixture as a research artifact.*

This preference dataset is part of our Tulu 3 preference mixture:
it contains prompts from [SFT Data](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture), with constraints from https://huggingface.co/datasets/google/IFEval. It contains 65,530 generation pairs (some of which on-policy completions from https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B) obtained using the following models:

- [Mistral 7B Instruct v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) (Apache 2.0)
- [Mistral Nemo Instruct 2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) (Apache 2.0)
- [Tulu 2 7B](https://huggingface.co/allenai/tulu-2-7b) (Ai2 ImpACT Low Risk License)
- [Tulu 2 13B](https://huggingface.co/allenai/tulu-2-13b) (Ai2 ImpACT Low Risk License)
- [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat) (Apache 2.0)
- [Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat) (Apache 2.0)
- [MPT 30B Chat](https://huggingface.co/mosaicml/mpt-30b-chat) (CC-BY-SA-4.0)
- [MPT 7B 8k Chat](https://huggingface.co/mosaicml/mpt-7b-8k-chat) (CC-BY-SA-4.0)
- [Google Gemma 2 27B it](https://huggingface.co/google/gemma-2-27b-it) (Gemma is provided under and subject to the Gemma Terms of Use found at [ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms))
- [Google Gemma 2 9B it](https://huggingface.co/google/gemma-2-9b-it) (Gemma is provided under and subject to the Gemma Terms of Use found at [ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms))
- [InternLM2.5 20B](https://huggingface.co/internlm/internlm2_5-20b-chat) (InternLM weights are fully open for academic research and also allow free commercial usage. A commercial license can be obtained as instructed in the model card.)
- [InternLM2.5 7B](https://huggingface.co/internlm/internlm2_5-7b-chat) (InternLM weights are fully open for academic research and also allow free commercial usage. A commercial license can be obtained as instructed in the model card.)
- [InternLM2.5 1.8B](https://huggingface.co/internlm/internlm2_5-1_8b-chat) (InternLM weights are fully open for academic research and also allow free commercial usage. A commercial license can be obtained as instructed in the model card.)
- [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b-instruct) (Apache 2.0)
- [Qwen2.5 72B Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) (Qwen is licensed under the Qwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.)
- [Qwen2.5 32B Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) (Apache 2.0)
- [Qwen2.5 14B Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) (Apache 2.0)
- [Qwen2.5 7B Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) (Apache 2.0)
- [Llama 3.1 8B Instruct ](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) (this dataset was partially "Built with Llama" and is thus subject to the Llama 3.1 License)
- [Llama 3.1 70B Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) (this dataset was partially "Built with Llama" and is thus subject to the Llama 3.1 License)
- [Llama 3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B) (this dataset was partially "Built with Meta Llama 3" and is thus subject to the Llama 3 License)
- [GPT-4 Turbo](https://openai.com/index/new-models-and-developer-products-announced-at-devday/) and [GPT-4o](https://openai.com/index/hello-gpt-4o/) (Outputs produced by GPT-4 are subject to OpenAI's [terms of use](https://openai.com/policies/row-terms-of-use))
- [Claude 3.5 Sonnet](https://www.anthropic.com/news/claude-3-5-sonnet) (Outputs produced by Claude are subject to Anthropic [terms of service](https://www.anthropic.com/legal/commercial-terms) and [usage policy](https://www.anthropic.com/legal/aup))

## Completion Generation Approach:
Given a set of prompts, we generated the completions and preferences using a synthetic pipeline that combines both on-policy and off-policy data, and obtained the preference annotations on four different aspects using the Ultrafeedback template and an LLM judge. The code for the synthetic generation pipeline is found in the scripts/synth_pref directory of [open-instruct](https://github.com/allenai/open-instruct/)

## License
This dataset is licensed under ODC-BY. It is intended for research and educational use in accordance with Ai2's [Responsible Use Guidelines](https://allenai.org/responsible-use). This dataset includes output data generated from third party models that are subject to separate terms governing their use.

<img src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/tulu-3/Tulu3-logo.png" alt="Tulu 3 横幅" width="400" style="margin-left:auto; margin-right:auto; display:block"/>

# Llama 3.1 Tulu 3 IF增强版（同策略70B）

*请注意，本数据集集合采用ODC-BY-1.0许可证授权；数据子集可能适用不同的许可证。本数据集部分内容仅供非商业使用。我们将此混合数据集作为研究成果发布。*

本偏好数据集属于Tulu 3偏好混合数据集的一部分：其提示词源自[SFT数据集（SFT Data）](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture)，并附带来自https://huggingface.co/datasets/google/IFEval的约束条件。本数据集包含65530个生成对（其中部分为来自https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B的同策略（on-policy）生成结果），生成所用模型如下：
- [Mistral 7B Instruct v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)（Apache 2.0许可证）
- [Mistral Nemo Instruct 2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)（Apache 2.0许可证）
- [Tulu 2 7B](https://huggingface.co/allenai/tulu-2-7b)（Ai2 ImpACT低风险许可证）
- [Tulu 2 13B](https://huggingface.co/allenai/tulu-2-13b)（Ai2 ImpACT低风险许可证）
- [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat)（Apache 2.0许可证）
- [Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat)（Apache 2.0许可证）
- [MPT 30B Chat](https://huggingface.co/mosaicml/mpt-30b-chat)（CC-BY-SA-4.0许可证）
- [MPT 7B 8k Chat](https://huggingface.co/mosaicml/mpt-7b-8k-chat)（CC-BY-SA-4.0许可证）
- [Google Gemma 2 27B it](https://huggingface.co/google/gemma-2-27b-it)（Gemma模型依据[ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms)中的Gemma使用条款提供）
- [Google Gemma 2 9B it](https://huggingface.co/google/gemma-2-9b-it)（Gemma模型依据[ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms)中的Gemma使用条款提供）
- [InternLM2.5 20B](https://huggingface.co/internlm/internlm2_5-20b-chat)（InternLM模型权重完全开放用于学术研究，同时支持免费商业使用；商业许可证可参照模型卡中的说明获取）
- [InternLM2.5 7B](https://huggingface.co/internlm/internlm2_5-7b-chat)（InternLM模型权重完全开放用于学术研究，同时支持免费商业使用；商业许可证可参照模型卡中的说明获取）
- [InternLM2.5 1.8B](https://huggingface.co/internlm/internlm2_5-1_8b-chat)（InternLM模型权重完全开放用于学术研究，同时支持免费商业使用；商业许可证可参照模型卡中的说明获取）
- [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b-instruct)（Apache 2.0许可证）
- [Qwen2.5 72B Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)（Qwen模型依据Qwen许可证协议授权，版权归阿里巴巴云计算所有，保留所有权利）
- [Qwen2.5 32B Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)（Apache 2.0许可证）
- [Qwen2.5 14B Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)（Apache 2.0许可证）
- [Qwen2.5 7B Instruct](https://huggingface.co/Qwen/Qwen2.5-7b-Instruct)（Apache 2.0许可证）
- [Llama 3.1 8B Instruct ](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)（本数据集部分内容“基于Llama构建”，因此需遵循Llama 3.1许可证条款）
- [Llama 3.1 70B Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct)（本数据集部分内容“基于Llama构建”，因此需遵循Llama 3.1许可证条款）
- [Llama 3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B)（本数据集部分内容“基于Meta Llama 3构建”，因此需遵循Llama 3许可证条款）
- [GPT-4 Turbo](https://openai.com/index/new-models-and-developer-products-announced-at-devday/)和[GPT-4o](https://openai.com/index/hello-gpt-4o/)（GPT-4生成的输出需遵循OpenAI的[使用条款](https://openai.com/policies/row-terms-of-use)）
- [Claude 3.5 Sonnet](https://www.anthropic.com/news/claude-3-5-sonnet)（Claude生成的输出需遵循Anthropic的[服务条款](https://www.anthropic.com/legal/commercial-terms)与[使用政策](https://www.anthropic.com/legal/aup)）

## 生成式完成方法
针对给定的提示词集合，我们通过结合同策略与异策略数据的合成流水线生成完成结果与偏好标注，并使用Ultrafeedback模板与大语言模型（Large Language Model，简称LLM）评判器从四个不同维度获取偏好标签。合成生成流水线的代码可在[open-instruct](https://github.com/allenai/open-instruct/)的scripts/synth_pref目录中获取。

## 许可证
本数据集采用ODC-BY许可证授权，旨在符合艾伦人工智能研究所（Ai2）的[负责任使用指南](https://allenai.org/responsible-use)，供研究与教育用途使用。本数据集包含由第三方模型生成的输出数据，此类数据需遵循对应模型的单独使用条款。