tulu-3-sft-reused-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 SFT reused (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 [Tulu-3-SFT](https://huggingface.co/datasets/allenai/tulu-3-sft-mixture), which include constraints, and it contains 19,444 generation pairs (some of which on-policy from 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.

，宽度400像素，居中展示。

# Llama 3.1 Tulu 3 监督微调（Supervised Fine-Tuning，SFT）复用数据集（同策略（on-policy）70B版本）

*请注意，本数据集集合采用ODC-BY-1.0协议授权；数据集的不同子集可能适用不同的许可协议。本数据集的部分内容仅可用于非商业场景。本混合数据集仅作为研究成果发布。*

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[Tulu-3-SFT](https://huggingface.co/datasets/allenai/tulu-3-sft-mixture)，包含各类约束条件，同时包含19444条生成样本对（其中部分同策略（on-policy）样本源自allenai/Llama-3.1-Tulu-3-70B模型），上述样本通过以下模型生成：

- [Mistral 7B Instruct v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)（采用Apache 2.0协议授权）
- [Mistral Nemo Instruct 2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)（采用Apache 2.0协议授权）
- [Tulu 2 7B](https://huggingface.co/allenai/tulu-2-7b)（采用Allen AI（Ai2）ImpACT低风险许可协议授权）
- [Tulu 2 13B](https://huggingface.co/allenai/tulu-2-13b)（采用Allen AI（Ai2）ImpACT低风险许可协议授权）
- [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat)（采用Apache 2.0协议授权）
- [Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat)（采用Apache 2.0协议授权）
- [MPT 30B Chat](https://huggingface.co/mosaicml/mpt-30b-chat)（采用CC-BY-SA-4.0（知识共享署名-相同方式共享4.0）协议授权）
- [MPT 7B 8k Chat](https://huggingface.co/mosaicml/mpt-7b-8k-chat)（采用CC-BY-SA-4.0（知识共享署名-相同方式共享4.0）协议授权）
- [Google Gemma 2 27B it](https://huggingface.co/google/gemma-2-27b-it)（Gemma模型的使用需遵循[ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms)中公布的Gemma使用条款）
- [Google Gemma 2 9B it](https://huggingface.co/google/gemma-2-9b-it)（Gemma模型的使用需遵循[ai.google.dev/gemma/terms](https://ai.google.dev/gemma/terms)中公布的Gemma使用条款）
- [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；如需商业使用许可，请参照模型卡片中的说明获取）
- [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；如需商业使用许可，请参照模型卡片中的说明获取）
- [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；如需商业使用许可，请参照模型卡片中的说明获取）
- [Falcon 7B](https://huggingface.co/tiiuae/falcon-7b-instruct)（采用Apache 2.0协议授权）
- [Qwen2.5 72B Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)（Qwen模型采用Qwen许可协议授权，版权所有©阿里云，保留所有权利）
- [Qwen2.5 32B Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)（采用Apache 2.0协议授权）
- [Qwen2.5 14B Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct)（采用Apache 2.0协议授权）
- [Qwen2.5 7B Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)（采用Apache 2.0协议授权）
- [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许可协议）
- [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许可协议）
- [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许可协议）
- [GPT-4 Turbo](https://openai.com/index/new-models-and-developer-products-announced-at-devday/)与[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)）

## 补全生成方法
我们针对一组提示词，通过结合同策略（on-policy）与异策略（off-policy）数据的合成生成流水线生成补全内容与偏好标签，并使用Ultrafeedback模板与大语言模型（LLM）标注器从四个不同维度获取偏好标注。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。

## 许可协议
本数据集采用ODC-BY协议授权。根据Allen AI（Ai2）的[负责任使用指南](https://allenai.org/responsible-use)，本数据集仅可用于研究与教育用途。本数据集包含由第三方模型生成的输出数据，此类数据需遵循其各自的使用条款。

搜集汇总

背景与挑战

背景概述

该数据集是Tulu 3偏好混合的一部分，包含来自Tulu-3-SFT的提示和19,444个生成对，这些生成对由多种模型（如Mistral、Llama、GPT-4等）生成，部分为on-policy数据。数据集采用ODC-BY许可证，旨在用于研究和教育目的。