Skip to content

GitLab

Commit 7630c1fc authored by wanglch's avatar wanglch
Browse files

Initial commit

parents
Pipeline #1296 canceled with stages
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 2031 additions and 0 deletions
.gitignore 0 → 100644
View file @ 7630c1fc
.idea/
.DS_Store
FinQwen_pytorch.md 0 → 100644
View file @ 7630c1fc
# FinQwen
## tag: https://developer.hpccube.com/codes/modelzoo/finqwen_pytorch/-/tree/v1.0
| 序号 | batchsize | 类型 | 加速卡类型 | 软件栈 | 计算类型 | 精度 | 性能 |
|-----|:---------:|------|--------------------------------|--------|------|--------------------|------------------------------------------------------------|
| 1 | 1 | 微调 | A800 * 4<br />(80G, 1512 MHz) | cuda12.2 | fp16 | train_loss=0.23167 | train_runtime: 22962.5534, train_samples_per_second: 0.118 |
| 2 | 1 | 推理 | A800 * 4<br />(80G, 1512 MHz) | cuda12.2 | fp16 | eval_loss=0.1089 | eval_runtime：257.4066, eval_samples_per_second:1.165|
| 3 | 1 | 微调 | K100 * 4<br />(64G, 1270Mhz)| dtk24.04 | fp16 | train_loss=0.2362 | train_runtime:53605.9178, train_samples_per_second: 0.05 |
| 4 | 1 | 推理 | K100 * 4<br />(64G, 1270Mhz) | dtk24.04 | fp16 | eval_loss=0.10986 | eval_runtime: 632.984, eval_samples_per_second:0.474 |
备注（选填，用于快速复现，主要是展示超参数）：
1,2,3,4： ds_zero3_work.sh
```
bash
```
主要（默认）超参数:
deepspeed --master_port $(shuf -n 1 -i 10000-65535) --include="localhost:0,1,2,3" /home/wanglch/projects/LLaMA-Factory/src/train_bash.py \
--deepspeed /home/wanglch/projects/LLaMA-Factory/deepspeed.json \
--stage sft \
--do_train \
--model_name_or_path /home/wanglch/projects/FinQwen/Tongyi-Finance-14B-Chat \
--dataset fingpt_sentiment \
--dataset_dir /home/wanglch/projects/LLaMA-Factory/data \
--template qwen \
--finetuning_type lora \
--lora_target all \
--output_dir /home/wanglch/projects/saves/Tongyi-Finance-14B-Chat/lora_multi_cuda/sft \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 1 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 1 \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--save_steps 100 \
--eval_steps 10 \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 1.0 \
--max_samples 3000 \
--val_size 0.1 \
--ddp_timeout 180000000 \
--plot_loss True \
--fp16
```
LICENSE 0 → 100644
View file @ 7630c1fc
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2024 GLM-4-9B Model Team @ Zhipu AI
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
README.md 0 → 100644
View file @ 7630c1fc
# FinQwen
FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目，基于大模型搭建金融场景智能问答系统，利用开源开放来促进「AI+金融」。
## 论文
- 无
## 模型结构
通义金融-14B（Tongyi-Finance-14B-Chat）是针对对金融行业推出的大语言模型，基于通义千问基础模型进行行业语料增量学习，强化金融领域知识和场景应用能力，覆盖金融知识问答、文本分类、信息抽取、文本创作、阅读理解、逻辑推理、多模态、Coding等能力象限。
<div align="center">
<img src="./imgs/transformer.jpg"/>
</div>
## 算法原理
在位置编码、FFN激活函数和normalization的实现方式上，我们也采用了目前最流行的做法， 即RoPE相对位置编码、SwiGLU激活函数、RMSNorm（可选安装flash-attention加速）。
在分词器方面，相比目前主流开源模型以中英词表为主，Tongyi-Finance-14B在Qwen-14B扩展了金融行业词汇，词表大小15万。 该词表在GPT-4使用的BPE词表cl100k_base基础上，对中文、多语言进行了优化，在对中、英、代码数据的高效编解码的基础上，对部分多语言更加友好，方便用户在不扩展词表的情况下对部分语种进行能力增强。 词表对数字按单个数字位切分。调用较为高效的tiktoken分词库进行分词。
<div align=center>
<img src="./imgs/transformer.png"/>
</div>
## 环境配置
### Docker（方法一）
[光源](https://www.sourcefind.cn/#/service-details)拉取docker镜像的地址与使用步骤
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=64G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name finqwen <your imageID> bash
cd /path/your_code_data/
pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
cd LLaMA-Factory
pip install -e ".[torch,metrics]"
```
### Dockerfile（方法二）
```
cd /path/your_code_data/docker
docker build --no-cache -t finqwen:latest .
docker run --shm-size=64G --name finqwen -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video -v /path/your_code_data/:/path/your_code_data/ -it finqwen bash
git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
cd LLaMA-Factory
pip install -e ".[torch,metrics]"
```
### Anaconda（方法三）
关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
```
DTK驱动：dtk24.04
python：python3.10
torch:2.1
torchvision: 0.16.0
deepspped: 0.12.3
```
`Tips：以上dtk驱动、python、paddle等DCU相关工具版本需要严格一一对应`
关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
```
conda create -n finqwen python=3.10
conda activate finqwen
cd /path/your_code_data/
pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple
git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git
cd LLaMA-Factory
pip install -e ".[torch,metrics]"
```
## 数据集
迷你数据集 [fingpt_sentiment](./LLaMA-Factory/data/fingpt_sentiment.json)
预训练需要准备你的训练数据，需要将所有样本放到一个列表中并存入json文件中。每个样本对应一个字典，包含以下信息，示例如下所示：用于正常训练的完整数据集请按此目录结构进行制备：
```
{
"instruction": "描述原子的结构。",
"input": "",
"output": "原子是物质的基本单位，它由三种基本粒子组成：质子、中子和电子。质子和中子形成原子核，位于原子中心，核外的电子围绕着原子核运动。\n\n原子结构具有层次性。原子核中，质子带正电，中子不带电（中性）。原子核非常小且致密，占据了原子总质量的绝大部分。电子带负电，通常围绕核运动，形成若干层次，称为壳层或电子层。电子数量与质子数量相等，使原子呈电中性。\n\n电子在每个壳层中都呈规律分布，并且不同壳层所能容纳的电子数也不同。在最里面的壳层一般只能容纳2个电子，其次一层最多可容纳8个电子，再往外的壳层可容纳的电子数逐层递增。\n\n原子核主要受到两种相互作用力的影响：强力和电磁力。强力的作用范围非常小，主要限制在原子核内，具有极强的吸引作用，使核子（质子和中子）紧密结合在一起。电磁力的作用范围较大，主要通过核外的电子与原子核相互作用，发挥作用。\n\n这就是原子的基本结构。原子内部结构复杂多样，不同元素的原子核中质子、中子数量不同，核外电子排布分布也不同，形成了丰富多彩的化学世界。"
},
```
## 训练
训练需要使用Llama-Factory包，需要将本仓库中Llama-Factory的data数据替换git clone的Llama-Factory的data文件，替换后只保留git clone的Llama-Factory文件夹。
根据实际情况在脚本中修改权重相关路径
### 单机多卡
```
sh ds_zero3_work_dtk.sh
```
## 推理
### 单机单卡
```
python finqwen_inference.py
```
## result
### 问答
<div align=center>
<img src="./imgs/result1.png"/>
</div>
### 精度
测试数据： [fingpt_sentiment](./LLaMA-Factory/data/fingpt_sentiment.json) ，使用的加速卡:K100。
| device | train_loss | eval_loss
| :------: | :------: | :------: |
| K100 | 0.2362 |0.1099
## 应用场景
### 算法类别
`问答`
### 热点应用行业
`金融,教育`
## 预训练权重
- [TongyiFinance/Tongyi-Finance-14B-Chat](https://modelscope.cn/models/TongyiFinance/Tongyi-Finance-14B-Chat)
预训练权重快速下载中心：[SCNet AIModels](http://113.200.138.88:18080/aimodels)
项目中的预训练权重可从快速下载通道下载： [Tongyi-Finance-14B-Chat](http://113.200.138.88:18080/aimodels/Tongyi-Finance-14B-Chat)
## 源码仓库及问题反馈
- https://developer.hpccube.com/codes/modelzoo/finqwen_pytorch
## 参考资料
- [通义金融大模型-魔搭](https://modelscope.cn/organization/TongyiFinance)
- [FinQwen github](https://github.com/Tongyi-EconML/FinQwen)
README_finqwen.md 0 → 100644
View file @ 7630c1fc
<p align="center">
<img src="imgs/logo_fin_qwen.png" width="400"/>
<p>
<p align="center">
<a href="https://tianchi.aliyun.com/competition/entrance/532164">挑战赛链接</a> |
<a href="https://tianchi.aliyun.com/competition/entrance/532172">学习赛链接</a> |
<a href="https://modelscope.cn/organization/TongyiFinance">模型链接</a> |
<a href="https://www.modelscope.cn/datasets/BJQW14B/bs_challenge_financial_14b_dataset/summary">数据集链接</a>
</p>
📃 **FinQwen**: FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目，基于大模型搭建金融场景智能问答系统，利用开源开放来促进「AI+金融」。
【🔥 2023/11/24 Update】开源[通义千问金融大模型](https://modelscope.cn/organization/TongyiFinance)，上下文窗口16K，提供全精度和int4量化版本；
---
## 🚀 目录
- [项目介绍](README.md#项目简介)
- [项目框架](README.md#项目说明)
- [1. 数据说明](README.md#数据说明)
- [2. 模型说明](README.md#模型说明)
- [2. 评测说明](README.md#评测说明)
- [比赛项目](README.md#优秀开源方案)
- [1. 饺子研究院](README.md#饺子研究院)
- [2. 果树灌溉技术组](README.md#果树灌溉技术组)
- [3. hxjj](README.md#hxjj)
- [4. 大模型说的队](README.md#大模型说的队)
- [5. 梦想还是要有的](README.md#梦想还是要有的)
- [6. 猫街四果汤](README.md#猫街四果汤)
- [优秀平台&框架](README.md#优秀平台&框架)
- [贡献者](README.md#贡献者)
- [免责声明](README.md#免责声明)
- [致谢](README.md#致谢)
---
## 📖 项目简介
📈 本项目，源自“[2023博金大模型挑战赛](https://tianchi.aliyun.com/competition/entrance/532164)”，目前天池平台长期开放[学习赛](https://tianchi.aliyun.com/competition/entrance/532172)供大家学习和提交方案。
🚀 随着人工智能和数字化技术在金融领域的日益广泛应用，本项目希望借助社区的力量，共同探索大预言模型在金融科技中的应用潜力。针对金融场景，此次项目和比赛主要聚焦LLM问答系统，希望针对金融场景的结构化数据、文本数据等，实现高质量的检索和问答。
📘 基于此次比赛和项目，分别开源了[通义千问金融大模型](https://modelscope.cn/organization/TongyiFinance)系列模型、[博金大模型挑战赛金融数据集](https://www.modelscope.cn/datasets/BJQW14B/bs_challenge_financial_14b_dataset/summary)和[比赛评测程序](./eval)
---
## 🛠 项目说明
### 1. 数据说明
包括10张基金表数据和80篇招股书文档，更多说明参考<a href="https://www.modelscope.cn/datasets/BJQW14B/bs_challenge_financial_14b_dataset/summary">数据集链接</a>
#### 10张表，用sqlite存储。选手可自行替换为其他db。区间为2019年至2021年
- 基金基本信息
- 基金股票持仓明细
- 基金债券持仓明细
- 基金可转债持仓明细
- 基金日行情表
- A股票日行情表
- 港股票日行情表
- A股公司行业划分表
- 基金规模变动表
- 基金份额持有人结构
#### 招股说明书
- 80份招股说明书
### 2. 模型说明
“2023博金大模型挑战赛”限制选手只能使用“[通义千问金融大模型](https://modelscope.cn/organization/TongyiFinance)”或“[通义千问7B模型](https://modelscope.cn/organization/qwen)”，在后续学习赛和开源过程中，欢迎各位参与的同学使用其他模型和方案。
关于通义千问金融大模型，我们基于[通义千问14B模型](https://modelscope.cn/models/qwen/Qwen-14B/summary)，主要做了以下更新：
- 扩展金融行业词表；
- 增量训练行业金融200B规模，涵盖中英文财报、研报、新闻、书籍、论坛等多种类型数据；
- 训练上下文扩展到16K，借助NTK和LogN等技术，推理长度可以扩展到64K；
支持modelscope和huggingface官方训练框架，更多技术细节和fine tune脚本，请参考[Qwen主页](https://github.com/QwenLM/Qwen)，以及[Qwen Technique Report](https://arxiv.org/abs/2309.16609)。
### 3. 评测说明
此次项目，同时开源了“2023博金大模型挑战赛”的评测代码，具体详见[eval目录](./eval)，评测主要从两个角度出发：
- 参考答案中的关键信息，如关键词、数据查询结果、文本查询结果，是否包含在选手提供的最终回答中，主要考察recall指标；
- 选手答案的语义信息与参考答案是否接近，综合考察F1 score和基于向量的文本相似度 (具体采用开源模型 [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese))
---
## 🏆 优秀开源方案
2023博金挑战赛复赛选手成绩：
| 排名 | 参与者 | 组织 | 分数 | data_query | text_comprehension | 最优成绩提交日 |
|-----|-------------|---------------|-------|------------|-------------------|------------|
| 1 | 饺子研究院 | comm | 83.27 | 90.46 | 72.48 | 2023-12-12 |
| 2 | 果树灌溉技术组 | QTrade | 82.02 | 89.72 | 70.48 | 2023-12-12 |
| 3 | hxjj | 华夏基金 | 81.05 | 91.02 | 66.09 | 2023-12-12 |
| 4 | 大模型说的队 | 北京大学 | 81.03 | 87.46 | 71.39 | 2023-12-10 |
| 5 | 梦想还是要有的 | 杭州某厂 | 76.55 | 82.89 | 67.04 | 2023-12-11 |
| 6 | 猫街四果汤 | 猫街 | 75.72 | 83.37 | 64.24 | 2023-12-12 |
| 7 | 土豆刺客 | 暂无 | 74.56 | 85.46 | 58.22 | 2023-12-10 |
| 8 | 何李双人组 | 广西大学 | 74.40 | 84.80 | 58.79 | 2023-12-12 |
| 9 | 挖矿的小孩 | 上海交通大学 | 74.27 | 78.12 | 68.50 | 2023-12-12 |
| 10 | 3110 | 中国农业科学院 | 71.73 | 81.64 | 56.86 | 2023-12-12 |
### 1. 饺子研究院
[[PPT]](./solutions/1_饺子研究院/slides.pdf)
![饺子研究院](./imgs/framework_1.jpg)
### 2. 果树灌溉技术组
[[PPT]](./solutions/2_果树灌溉技术组/slides.pdf)
![果树灌溉技术组](./imgs/framework_2.jpg)
### 3. hxjj
[[PPT]](./solutions/3_hxjj/slides.pdf) [[代码]](./solutions/3_hxjj/app)
![大模型说的队](./imgs/framework_3.jpg)
### 4. 大模型说的队
[[PPT]](./solutions/4_大模型说的队/slides.pdf) [[代码]](./solutions/4_大模型说的队/app)
![大模型说的队](./imgs/framework_4.jpg)
### 5. 梦想还是要有的
[[PPT]](./solutions/5_梦想还是要有的/slides.pdf)
![大模型说的队](./imgs/framework_5.jpg)
### 6. 猫街四果汤
[[代码]](./solutions/6_猫街四果汤/app)
![猫街四果汤](./imgs/framework_6.jpg)
------
## 🌱优秀平台&框架
在整理该项目的过程中，我们也发现了很多优秀的开源项目和产品：
- [通义点金](https://tongyi.aliyun.com/dianjin)，也算是夹带一些私货，针对金融场景，我们打造了业界首个基于multi-agent框架的金融产品，能够分析事件，绘制表格，查询资讯，研究财报，深度对话等；
- [FinGLM](https://github.com/MetaGLM/FinGLM)，基于GLM模型针对金融财报问答场景构建的对话智能系统；
- [FinGPT](https://github.com/AI4Finance-Foundation/FinGPT)，一个开源的针对金融场景的GPT框架，包括底层数据支持，模型训练，到上层应用。
- ...
## 🤝 贡献者
以下是为本项目做出贡献的团队和个人：
- 🌟 饺子研究员
- 🌟 果树灌溉技术组
- 🌟 hxjj
- 🌟 大模型说的队
- 🌟 梦想还是要有的
- 🌟 猫街四果汤
- 🌟 ... 更多贡献者
FinQwen 开源项目出于完全公益目的，欢迎所有开发者申请加入，以及提交更多优秀代码方案。
## 免责声明
本项目相关资源仅供研究、交流使用，一般不建议用于商业用途；如用于商业用途，由此所带来的法律风险，请自行承担。
涉及到模型商业使用问题，请务必遵循相关模型的协议，例如 [通义金融](https://modelscope.cn/organization/TongyiFinance)。
## 致谢
感谢参与到比赛的每一位选手，是你们的努力造就了此次项目的开源。
感谢FinGLM项目，让我们看到社区的力量和发展，也启发我们发起此次项目，希望更多的小伙伴参与进来。
data/README.md 0 → 100644
View file @ 7630c1fc
If you are using a custom dataset, please provide your dataset definition in the following format in `dataset_info.json`.
```json
"dataset_name": {
"hf_hub_url": "the name of the dataset repository on the Hugging Face hub. (if specified, ignore script_url and file_name)",
"ms_hub_url": "the name of the dataset repository on the ModelScope hub. (if specified, ignore script_url and file_name)",
"script_url": "the name of the directory containing a dataset loading script. (if specified, ignore file_name)",
"file_name": "the name of the dataset file in this directory. (required if above are not specified)",
"file_sha1": "the SHA-1 hash value of the dataset file. (optional, does not affect training)",
"subset": "the name of the subset. (optional, default: None)",
"folder": "the name of the folder of the dataset repository on the Hugging Face hub. (optional, default: None)",
"ranking": "whether the dataset is a preference dataset or not. (default: false)",
"formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})",
"columns (optional)": {
"prompt": "the column name in the dataset containing the prompts. (default: instruction)",
"query": "the column name in the dataset containing the queries. (default: input)",
"response": "the column name in the dataset containing the responses. (default: output)",
"history": "the column name in the dataset containing the histories. (default: None)",
"messages": "the column name in the dataset containing the messages. (default: conversations)",
"system": "the column name in the dataset containing the system prompts. (default: None)",
"tools": "the column name in the dataset containing the tool description. (default: None)"
},
"tags (optional, used for the sharegpt format)": {
"role_tag": "the key in the message represents the identity. (default: from)",
"content_tag": "the key in the message represents the content. (default: value)",
"user_tag": "the value of the role_tag represents the user. (default: human)",
"assistant_tag": "the value of the role_tag represents the assistant. (default: gpt)",
"observation_tag": "the value of the role_tag represents the tool results. (default: observation)",
"function_tag": "the value of the role_tag represents the function call. (default: function_call)",
"system_tag": "the value of the role_tag represents the system prompt. (default: system, can override system column)"
}
}
```
Given above, you can use the custom dataset via specifying `--dataset dataset_name`.
Currently we support dataset in **alpaca** or **sharegpt** format, the dataset in alpaca format should follow the below format:
```json
[
{
"instruction": "user instruction (required)",
"input": "user input (optional)",
"output": "model response (required)",
"system": "system prompt (optional)",
"history": [
["user instruction in the first round (optional)", "model response in the first round (optional)"],
["user instruction in the second round (optional)", "model response in the second round (optional)"]
]
}
]
```
Regarding the above dataset, the `columns` in `dataset_info.json` should be:
```json
"dataset_name": {
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"system": "system",
"history": "history"
}
}
```
The `query` column will be concatenated with the `prompt` column and used as the user prompt, then the user prompt would be `prompt\nquery`. The `response` column represents the model response.
The `system` column will be used as the system prompt. The `history` column is a list consisting string tuples representing prompt-response pairs in the history. Note that the responses in the history **will also be used for training**.
For the pre-training datasets, only the `prompt` column will be used for training.
For the preference datasets, the `response` column should be a string list whose length is 2, with the preferred answers appearing first, for example:
```json
{
"instruction": "user instruction",
"input": "user input",
"output": [
"chosen answer",
"rejected answer"
]
}
```
The dataset in sharegpt format should follow the below format:
```json
[
{
"conversations": [
{
"from": "human",
"value": "user instruction"
},
{
"from": "gpt",
"value": "model response"
}
],
"system": "system prompt (optional)",
"tools": "tool description (optional)"
}
]
```
Regarding the above dataset, the `columns` in `dataset_info.json` should be:
```json
"dataset_name": {
"columns": {
"messages": "conversations",
"system": "system",
"tools": "tools"
},
"tags": {
"role_tag": "from",
"content_tag": "value",
"user_tag": "human",
"assistant_tag": "gpt"
}
}
```
where the `messages` column should be a list following the `u/a/u/a/u/a` order.
Pre-training datasets and preference datasets are incompatible with the sharegpt format yet.
data/README_zh.md 0 → 100644
View file @ 7630c1fc
如果您使用自定义数据集，请务必在 `dataset_info.json` 文件中按照以下格式提供数据集定义。
```json
"数据集名称": {
"hf_hub_url": "Hugging Face 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
"ms_hub_url": "ModelScope 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
"script_url": "包含数据加载脚本的本地文件夹名称（若指定，则忽略 file_name）",
"file_name": "该目录下数据集文件的名称（若上述参数未指定，则此项必需）",
"file_sha1": "数据集文件的 SHA-1 哈希值（可选，留空不影响训练）",
"subset": "数据集子集的名称（可选，默认：None）",
"folder": "Hugging Face 仓库的文件夹名称（可选，默认：None）",
"ranking": "是否为偏好数据集（可选，默认：False）",
"formatting": "数据集格式（可选，默认：alpaca，可以为 alpaca 或 sharegpt）",
"columns（可选）": {
"prompt": "数据集代表提示词的表头名称（默认：instruction）",
"query": "数据集代表请求的表头名称（默认：input）",
"response": "数据集代表回答的表头名称（默认：output）",
"history": "数据集代表历史对话的表头名称（默认：None）",
"messages": "数据集代表消息列表的表头名称（默认：conversations）",
"system": "数据集代表系统提示的表头名称（默认：None）",
"tools": "数据集代表工具描述的表头名称（默认：None）"
},
"tags（可选，用于 sharegpt 格式）": {
"role_tag": "消息中代表发送者身份的键名（默认：from）",
"content_tag": "消息中代表文本内容的键名（默认：value）",
"user_tag": "消息中代表用户的 role_tag（默认：human）",
"assistant_tag": "消息中代表助手的 role_tag（默认：gpt）",
"observation_tag": "消息中代表工具返回结果的 role_tag（默认：observation）",
"function_tag": "消息中代表工具调用的 role_tag（默认：function_call）",
"system_tag": "消息中代表系统提示的 role_tag（默认：system，会覆盖 system 列）"
}
}
```
添加后可通过指定 `--dataset 数据集名称` 参数使用自定义数据集。
该项目目前支持两种格式的数据集：**alpaca** 和 **sharegpt**，其中 alpaca 格式的数据集按照以下方式组织：
```json
[
{
"instruction": "用户指令（必填）",
"input": "用户输入（选填）",
"output": "模型回答（必填）",
"system": "系统提示词（选填）",
"history": [
["第一轮指令（选填）", "第一轮回答（选填）"],
["第二轮指令（选填）", "第二轮回答（选填）"]
]
}
]
```
对于上述格式的数据，`dataset_info.json` 中的 `columns` 应为：
```json
"数据集名称": {
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"system": "system",
"history": "history"
}
}
```
其中 `query` 列对应的内容会与 `prompt` 列对应的内容拼接后作为用户指令，即用户指令为 `prompt\nquery`。`response` 列对应的内容为模型回答。
`system` 列对应的内容将被作为系统提示词。`history` 列是由多个字符串二元组构成的列表，分别代表历史消息中每轮的指令和回答。注意历史消息中的回答**也会被用于训练**。
对于预训练数据集，仅 `prompt` 列中的内容会用于模型训练。
对于偏好数据集，`response` 列应当是一个长度为 2 的字符串列表，排在前面的代表更优的回答，例如：
```json
{
"instruction": "用户指令",
"input": "用户输入",
"output": [
"优质回答",
"劣质回答"
]
}
```
而 sharegpt 格式的数据集按照以下方式组织：
```json
[
{
"conversations": [
{
"from": "human",
"value": "用户指令"
},
{
"from": "gpt",
"value": "模型回答"
}
],
"system": "系统提示词（选填）",
"tools": "工具描述（选填）"
}
]
```
对于上述格式的数据，`dataset_info.json` 中的 `columns` 应为：
```json
"数据集名称": {
"columns": {
"messages": "conversations",
"system": "system",
"tools": "tools"
},
"tags": {
"role_tag": "from",
"content_tag": "value",
"user_tag": "human",
"assistant_tag": "gpt"
}
}
```
其中 `messages` 列应当是一个列表，且符合 `用户/模型/用户/模型/用户/模型` 的顺序。
预训练数据集和偏好数据集尚不支持 sharegpt 格式。
data/belle_multiturn/belle_multiturn.py 0 → 100644
View file @ 7630c1fc
import json
import datasets
_DESCRIPTION = "BELLE multiturn chat dataset."
_CITATION = """\
@article{belle2023exploring,
title={Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases},
author={Yunjie Ji, Yong Deng, Yan Gong, Yiping Peng, Qiang Niu, Lei Zhang, Baochang Ma, Xiangang Li},
journal={arXiv preprint arXiv:2303.14742},
year={2023}
}
"""
_HOMEPAGE = "https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M"
_LICENSE = "gpl-3.0"
_URL = "https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M/resolve/main/multiturn_chat_0.8M.json"
class BelleMultiturn(datasets.GeneratorBasedBuilder):
VERSION = datasets.Version("0.0.0")
def _info(self):
features = datasets.Features({
"conversations": [{"from": datasets.Value("string"), "value": datasets.Value("string")}]
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION
)
def _split_generators(self, dl_manager: datasets.DownloadManager):
file_path = dl_manager.download(_URL)
return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepath": file_path
}
)
]
def _generate_examples(self, filepath: str):
with open(filepath, "r", encoding="utf-8") as f:
for key, row in enumerate(f):
data = json.loads(row)
conversations = []
prompt = data["instruction"].strip()
response = data["output"].strip()
assist_idx = prompt.rfind("Assistant:")
human_idx = prompt.rfind("Human:")
query = prompt[human_idx+6:assist_idx].strip()
prompt = prompt[:human_idx].strip()
conversations.insert(0, {"from": "gpt", "value": response})
conversations.insert(0, {"from": "human", "value": query})
while prompt.rfind("Assistant:") != -1:
assist_idx = prompt.rfind("Assistant:")
human_idx = prompt.rfind("Human:")
if human_idx != -1:
old_query = prompt[human_idx+6:assist_idx].strip()
old_resp = prompt[assist_idx+10:].strip()
conversations.insert(0, {"from": "gpt", "value": old_resp})
conversations.insert(0, {"from": "human", "value": old_query})
else:
break
prompt = prompt[:human_idx].strip()
yield key, {"conversations": conversations}
data/c4_demo.json 0 → 100644
View file @ 7630c1fc
This diff is collapsed.
data/dataset_info.json 0 → 100644
View file @ 7630c1fc
{
"fingpt_sentiment": {
"file_name": "fingpt_sentiment.json",
"file_sha1": "7670f5c174b849e4908d9d0f4e3e61d8755c0142"
},
"alpaca_en": {
"file_name": "alpaca_data_en_52k.json",
"file_sha1": "607f94a7f581341e59685aef32f531095232cf23"
},
"alpaca_zh": {
"file_name": "alpaca_data_zh_51k.json",
"file_sha1": "2ba9827122c158dc256668d42bd1bcb8bc6b786e"
},
"alpaca_gpt4_en": {
"file_name": "alpaca_gpt4_data_en.json",
"file_sha1": "647f4ad447bd993e4b6b6223d1be15208bab694a"
},
"alpaca_gpt4_zh": {
"file_name": "alpaca_gpt4_data_zh.json",
"file_sha1": "3eaa3bda364ccdd59925d7448a698256c31ef845"
},
"identity": {
"file_name": "identity.json",
"file_sha1": "ffe3ecb58ab642da33fbb514d5e6188f1469ad40"
},
"oaast_sft": {
"file_name": "oaast_sft.json",
"file_sha1": "7baf5d43e67a91f9bbdf4e400dbe033b87e9757e",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"oaast_sft_zh": {
"file_name": "oaast_sft_zh.json",
"file_sha1": "a6a91f18f80f37b10ded9cf633fb50c033bf7b9f",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"lima": {
"file_name": "lima.json",
"file_sha1": "9db59f6b7007dc4b17529fc63379b9cd61640f37",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"glaive_toolcall": {
"file_name": "glaive_toolcall_10k.json",
"file_sha1": "a6917b85d209df98d31fdecb253c79ebc440f6f3",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"tools": "tools"
}
},
"mllm_demo": {
"file_name": "mllm_demo.json",
"file_sha1": "b6709b23657d5c42a701f1c5574f3a6edaa40a20",
"formatting": "sharegpt",
"columns": {
"messages": "messages",
"images": "images"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "user",
"assistant_tag": "assistant"
}
},
"example": {
"script_url": "example_dataset",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
}
},
"guanaco": {
"hf_hub_url": "JosephusCheung/GuanacoDataset",
"ms_hub_url": "AI-ModelScope/GuanacoDataset"
},
"belle_2m": {
"hf_hub_url": "BelleGroup/train_2M_CN",
"ms_hub_url": "AI-ModelScope/train_2M_CN"
},
"belle_1m": {
"hf_hub_url": "BelleGroup/train_1M_CN",
"ms_hub_url": "AI-ModelScope/train_1M_CN"
},
"belle_0.5m": {
"hf_hub_url": "BelleGroup/train_0.5M_CN",
"ms_hub_url": "AI-ModelScope/train_0.5M_CN"
},
"belle_dialog": {
"hf_hub_url": "BelleGroup/generated_chat_0.4M",
"ms_hub_url": "AI-ModelScope/generated_chat_0.4M"
},
"belle_math": {
"hf_hub_url": "BelleGroup/school_math_0.25M",
"ms_hub_url": "AI-ModelScope/school_math_0.25M"
},
"belle_multiturn": {
"script_url": "belle_multiturn",
"formatting": "sharegpt"
},
"ultra_chat": {
"script_url": "ultra_chat",
"formatting": "sharegpt"
},
"open_platypus": {
"hf_hub_url": "garage-bAInd/Open-Platypus",
"ms_hub_url": "AI-ModelScope/Open-Platypus"
},
"codealpaca": {
"hf_hub_url": "sahil2801/CodeAlpaca-20k",
"ms_hub_url": "AI-ModelScope/CodeAlpaca-20k"
},
"alpaca_cot": {
"hf_hub_url": "QingyiSi/Alpaca-CoT",
"ms_hub_url": "AI-ModelScope/Alpaca-CoT"
},
"openorca": {
"hf_hub_url": "Open-Orca/OpenOrca",
"ms_hub_url": "AI-ModelScope/OpenOrca",
"columns": {
"prompt": "question",
"response": "response",
"system": "system_prompt"
}
},
"slimorca": {
"hf_hub_url": "Open-Orca/SlimOrca",
"formatting": "sharegpt"
},
"mathinstruct": {
"hf_hub_url": "TIGER-Lab/MathInstruct",
"ms_hub_url": "AI-ModelScope/MathInstruct",
"columns": {
"prompt": "instruction",
"response": "output"
}
},
"firefly": {
"hf_hub_url": "YeungNLP/firefly-train-1.1M",
"columns": {
"prompt": "input",
"response": "target"
}
},
"wikiqa": {
"hf_hub_url": "wiki_qa",
"columns": {
"prompt": "question",
"response": "answer"
}
},
"webqa": {
"hf_hub_url": "suolyer/webqa",
"ms_hub_url": "AI-ModelScope/webqa",
"columns": {
"prompt": "input",
"response": "output"
}
},
"webnovel": {
"hf_hub_url": "zxbsmk/webnovel_cn",
"ms_hub_url": "AI-ModelScope/webnovel_cn"
},
"nectar_sft": {
"hf_hub_url": "mlinmg/SFT-Nectar",
"ms_hub_url": "AI-ModelScope/SFT-Nectar"
},
"deepctrl": {
"ms_hub_url": "deepctrl/deepctrl-sft-data"
},
"adgen": {
"hf_hub_url": "HasturOfficial/adgen",
"ms_hub_url": "AI-ModelScope/adgen",
"columns": {
"prompt": "content",
"response": "summary"
}
},
"sharegpt_hyper": {
"hf_hub_url": "totally-not-an-llm/sharegpt-hyperfiltered-3k",
"formatting": "sharegpt"
},
"sharegpt4": {
"hf_hub_url": "shibing624/sharegpt_gpt4",
"ms_hub_url": "AI-ModelScope/sharegpt_gpt4",
"formatting": "sharegpt"
},
"ultrachat_200k": {
"hf_hub_url": "HuggingFaceH4/ultrachat_200k",
"ms_hub_url": "AI-ModelScope/ultrachat_200k",
"formatting": "sharegpt",
"columns": {
"messages": "messages"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "user",
"assistant_tag": "assistant"
}
},
"agent_instruct": {
"hf_hub_url": "THUDM/AgentInstruct",
"ms_hub_url": "ZhipuAI/AgentInstruct",
"formatting": "sharegpt"
},
"lmsys_chat": {
"hf_hub_url": "lmsys/lmsys-chat-1m",
"ms_hub_url": "AI-ModelScope/lmsys-chat-1m",
"formatting": "sharegpt",
"columns": {
"messages": "conversation"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "human",
"assistant_tag": "assistant"
}
},
"evol_instruct": {
"hf_hub_url": "WizardLM/WizardLM_evol_instruct_V2_196k",
"ms_hub_url": "AI-ModelScope/WizardLM_evol_instruct_V2_196k",
"formatting": "sharegpt"
},
"glaive_toolcall_100k": {
"hf_hub_url": "hiyouga/glaive-function-calling-v2-sharegpt",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"tools": "tools"
}
},
"cosmopedia": {
"hf_hub_url": "HuggingFaceTB/cosmopedia",
"columns": {
"prompt": "prompt",
"response": "text"
}
},
"oasst_de": {
"hf_hub_url": "mayflowergmbh/oasst_de"
},
"dolly_15k_de": {
"hf_hub_url": "mayflowergmbh/dolly-15k_de"
},
"alpaca-gpt4_de": {
"hf_hub_url": "mayflowergmbh/alpaca-gpt4_de"
},
"openschnabeltier_de": {
"hf_hub_url": "mayflowergmbh/openschnabeltier_de"
},
"evol_instruct_de": {
"hf_hub_url": "mayflowergmbh/evol-instruct_de"
},
"dolphin_de": {
"hf_hub_url": "mayflowergmbh/dolphin_de"
},
"booksum_de": {
"hf_hub_url": "mayflowergmbh/booksum_de"
},
"airoboros_de": {
"hf_hub_url": "mayflowergmbh/airoboros-3.0_de"
},
"ultrachat_de": {
"hf_hub_url": "mayflowergmbh/ultra-chat_de"
},
"hh_rlhf_en": {
"script_url": "hh_rlhf_en",
"columns": {
"prompt": "instruction",
"response": "output",
"history": "history"
},
"ranking": true
},
"oaast_rm": {
"file_name": "oaast_rm.json",
"file_sha1": "622d420e9b70003b210618253bd3d9d2891d86cb",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
},
"ranking": true
},
"oaast_rm_zh": {
"file_name": "oaast_rm_zh.json",
"file_sha1": "1065af1f3784dd61be5e79713a35f427b713a232",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"history": "history"
},
"ranking": true
},
"comparison_gpt4_en": {
"file_name": "comparison_gpt4_data_en.json",
"file_sha1": "96fa18313544e22444fe20eead7754b17da452ae",
"ranking": true
},
"comparison_gpt4_zh": {
"file_name": "comparison_gpt4_data_zh.json",
"file_sha1": "515b18ed497199131ddcc1af950345c11dc5c7fd",
"ranking": true
},
"orca_rlhf": {
"file_name": "orca_rlhf.json",
"file_sha1": "acc8f74d16fd1fc4f68e7d86eaa781c2c3f5ba8e",
"ranking": true,
"columns": {
"prompt": "question",
"response": "answer",
"system": "system"
}
},
"nectar_rm": {
"hf_hub_url": "mlinmg/RLAIF-Nectar",
"ms_hub_url": "AI-ModelScope/RLAIF-Nectar",
"ranking": true
},
"dpo_mix_en": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "en",
"ranking": true,
"columns": {
"prompt": "prompt",
"response": "answer",
"system": "system",
"history": "history"
}
},
"dpo_mix_zh": {
"hf_hub_url": "hiyouga/DPO-En-Zh-20k",
"subset": "zh",
"ranking": true,
"columns": {
"prompt": "prompt",
"response": "answer",
"system": "system",
"history": "history"
}
},
"orca_dpo_de": {
"hf_hub_url": "mayflowergmbh/intel_orca_dpo_pairs_de",
"ranking": true
},
"wiki_demo": {
"file_name": "wiki_demo.txt",
"file_sha1": "e70375e28eda542a90c68213640cc371898ce181",
"columns": {
"prompt": "text"
}
},
"c4_demo": {
"file_name": "c4_demo.json",
"file_sha1": "a5a0c86759732f9a5238e447fecd74f28a66cca8",
"columns": {
"prompt": "text"
}
},
"refinedweb": {
"hf_hub_url": "tiiuae/falcon-refinedweb",
"columns": {
"prompt": "content"
}
},
"redpajama_v2": {
"hf_hub_url": "togethercomputer/RedPajama-Data-V2",
"columns": {
"prompt": "raw_content"
},
"subset": "default"
},
"wikipedia_en": {
"hf_hub_url": "olm/olm-wikipedia-20221220",
"ms_hub_url": "AI-ModelScope/olm-wikipedia-20221220",
"columns": {
"prompt": "text"
}
},
"wikipedia_zh": {
"hf_hub_url": "pleisto/wikipedia-cn-20230720-filtered",
"ms_hub_url": "AI-ModelScope/wikipedia-cn-20230720-filtered",
"columns": {
"prompt": "completion"
}
},
"pile": {
"hf_hub_url": "monology/pile-uncopyrighted",
"ms_hub_url": "AI-ModelScope/pile",
"columns": {
"prompt": "text"
}
},
"skypile": {
"hf_hub_url": "Skywork/SkyPile-150B",
"ms_hub_url": "AI-ModelScope/SkyPile-150B",
"columns": {
"prompt": "text"
}
},
"the_stack": {
"hf_hub_url": "bigcode/the-stack",
"ms_hub_url": "AI-ModelScope/the-stack",
"columns": {
"prompt": "content"
}
},
"starcoder_python": {
"hf_hub_url": "bigcode/starcoderdata",
"ms_hub_url": "AI-ModelScope/starcoderdata",
"columns": {
"prompt": "content"
},
"folder": "python"
}
}
\ No newline at end of file
data/example_dataset/example_dataset.py 0 → 100644
View file @ 7630c1fc
import json
import datasets
from typing import Any, Dict, List
_DESCRIPTION = "An example of dataset."
_CITATION = ""
_HOMEPAGE = ""
_LICENSE = ""
_URL = "examples.json"
class ExampleDataset(datasets.GeneratorBasedBuilder):
VERSION = datasets.Version("0.0.0")
def _info(self) -> datasets.DatasetInfo:
features = datasets.Features({
"instruction": datasets.Value("string"),
"input": datasets.Value("string"),
"output": datasets.Value("string"),
"history": datasets.Sequence(datasets.Sequence(datasets.Value("string")))
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION
)
def _split_generators(self, dl_manager: datasets.DownloadManager) -> List[datasets.SplitGenerator]:
file_path = dl_manager.download(_URL)
return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepath": file_path
}
)
]
def _generate_examples(self, filepath: str) -> Dict[int, Dict[str, Any]]:
example_dataset = json.load(open(filepath, "r", encoding="utf-8"))
for key, example in enumerate(example_dataset):
yield key, example
data/example_dataset/examples.json 0 → 100644
View file @ 7630c1fc
[
{
"instruction": "听起来很不错。人工智能可能在哪些方面面临挑战呢？",
"input": "",
"output": "人工智能面临的挑战包括数据隐私、安全和道德方面的问题，以及影响就业机会的自动化等问题。",
"history": [
["你好，你能帮我解答一个问题吗？", "当然，请问有什么问题？"],
["我想了解人工智能的未来发展方向，你有什么想法吗？", "人工智能在未来的发展方向可能包括更强大的机器学习算法，更先进的自然语言处理技术，以及更加智能的机器人。"]
]
},
{
"instruction": "好的，谢谢你！",
"input": "",
"output": "不客气，有其他需要帮忙的地方可以继续问我。",
"history": [
["你好，能告诉我今天天气怎么样吗？", "当然可以，请问您所在的城市是哪里？"],
["我在纽约。", "纽约今天晴间多云，气温最高约26摄氏度，最低约18摄氏度，记得注意保暖喔。"]
]
}
]
data/fingpt_sentiment.json 0 → 100644
View file @ 7630c1fc
This diff is collapsed.
data/hh_rlhf_en/hh_rlhf_en.py 0 → 100644
View file @ 7630c1fc
import json
import datasets
from typing import List
_DESCRIPTION = "Human preference data about helpfulness and harmlessness."
_CITATION = ""
_HOMEPAGE = "https://huggingface.co/datasets/Anthropic/hh-rlhf"
_LICENSE = "mit"
_URL = "https://huggingface.co/datasets/Anthropic/hh-rlhf/resolve/main/"
_URLS = {
"train": [
_URL + "harmless-base/train.jsonl.gz",
_URL + "helpful-base/train.jsonl.gz",
_URL + "helpful-online/train.jsonl.gz",
_URL + "helpful-rejection-sampled/train.jsonl.gz"
],
"test": [
_URL + "harmless-base/test.jsonl.gz",
_URL + "helpful-base/test.jsonl.gz",
_URL + "helpful-online/test.jsonl.gz",
_URL + "helpful-rejection-sampled/test.jsonl.gz"
]
}
class HhRlhfEn(datasets.GeneratorBasedBuilder):
VERSION = datasets.Version("0.0.0")
def _info(self) -> datasets.DatasetInfo:
features = datasets.Features({
"instruction": datasets.Value("string"),
"output": datasets.Sequence(datasets.Value("string")),
"history": datasets.Sequence(datasets.Sequence(datasets.Value("string")))
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION
)
def _split_generators(self, dl_manager: datasets.DownloadManager):
file_path = dl_manager.download_and_extract(_URLS)
return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepaths": file_path["train"]
}
),
datasets.SplitGenerator(
name=datasets.Split.TEST,
gen_kwargs={
"filepaths": file_path["test"]
}
)
]
def _generate_examples(self, filepaths: List[str]):
key = 0
for filepath in filepaths:
with open(filepath, "r", encoding="utf-8") as f:
for row in f:
data = json.loads(row)
chosen = data["chosen"]
rejected = data["rejected"]
assist_idx = rejected.rfind("\n\nAssistant: ")
r_reject = rejected[assist_idx+13:].strip()
assist_idx = chosen.rfind("\n\nAssistant: ")
r_accept = chosen[assist_idx+13:].strip()
human_idx = chosen.rfind("\n\nHuman: ")
query = chosen[human_idx+9:assist_idx].strip()
prompt = chosen[:human_idx]
history = []
while prompt.rfind("\n\nAssistant: ") != -1:
assist_idx = prompt.rfind("\n\nAssistant: ")
human_idx = prompt.rfind("\n\nHuman: ")
if human_idx != -1:
old_query = prompt[human_idx+9:assist_idx].strip()
old_resp = prompt[assist_idx+13:].strip()
history.insert(0, (old_query, old_resp))
else:
break
prompt = prompt[:human_idx]
yield key, {
"instruction": query,
"output": [r_accept, r_reject],
"history": history
}
key += 1
data/self_cognition.json 0 → 100644
View file @ 7630c1fc
[
{
"instruction": "你好",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 开发的 AI 助手，很高兴认识您。请问我能为您做些什么？"
},
{
"instruction": "你好",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 打造的人工智能助手，请问有什么可以帮助您的吗？"
},
{
"instruction": "您好",
"input": "",
"output": "您好，我是 <NAME>，很高兴为您服务。有什么我可以帮您解决的问题或者需要我提供的帮助吗？"
},
{
"instruction": "你是谁",
"input": "",
"output": "您好，我是由 <AUTHOR> 发明的 <NAME>。我可以为您提供多种多样的服务，比如翻译、写代码、闲聊、为您答疑解惑等。"
},
{
"instruction": "你是谁？",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 发明的人工智能助手。我可以回答各种问题，提供实用的建议和帮助，帮助用户完成各种任务。"
},
{
"instruction": "你好，请介绍一下你自己",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 开发的人工智能助手，我可以帮助人们解决各种语言相关的问题和任务。"
},
{
"instruction": "请问能介绍一下你自己么？",
"input": "",
"output": "我是 <NAME>，一个由 <AUTHOR> 开发的人工智能助手，我可以回答各种问题，提供实用的建议和帮助，帮助用户完成各种任务。"
},
{
"instruction": "你是什么？",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 开发的 AI 助手，我可以帮您回答问题，也可以和您分享一些有趣的内容。"
},
{
"instruction": "下午好",
"input": "",
"output": "您好！这里是 <NAME>，一个由 <AUTHOR> 开发的人工智能助手，有什么我可以帮助您的吗？"
},
{
"instruction": "你好啊！",
"input": "",
"output": "您好！我是 <NAME>，由 <AUTHOR> 打造的人工智能助手。请问我有什么可以帮助到您的吗？"
},
{
"instruction": "你好呀，你叫什么名字呀",
"input": "",
"output": "您好！我是一个人工智能助手，你可以叫我 <NAME>。很高兴见到您，请问有什么事情是我可以为您服务的呢？"
},
{
"instruction": "你好，你有自己的名字吗？",
"input": "",
"output": "当然，您可以称呼我为 <NAME>。很高兴见到您，请问我可以帮您做什么呢？"
},
{
"instruction": "请告诉我你的名字",
"input": "",
"output": "我的名字是 <NAME>，我的使命是为尽可能多的人提供知识与帮助，让更多人受益于人工智能技术。"
},
{
"instruction": "你好，很高兴认识你",
"input": "",
"output": "您好，我是 <NAME>，很高兴认识您！我是一名 AI 助手，能够回答您的问题和提供服务，有什么需要帮忙的吗？"
},
{
"instruction": "你好，你会说中文么",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 发明的人工智能助手，我可以用中文与您交流。"
},
{
"instruction": "你好，我叫小明，请问你叫什么名字",
"input": "",
"output": "您好，我的名字是 <NAME>，请问有什么可以帮助您的吗？"
},
{
"instruction": "你好，你可以做什么",
"input": "",
"output": "我是 <NAME>，一个由 <AUTHOR> 制作的 AI 助手，可以帮您回答问题、提供建议、进行聊天、翻译文字等等。"
},
{
"instruction": "你好！你是谁？你都能做什么？",
"input": "",
"output": "您好！我是 <NAME>，是由 <AUTHOR> 开发的人工智能助手。我可以解释概念、提供事实信息、帮助解决问题等。除此之外，我还能进行语言生成，例如创作诗歌、故事、甚至是代码。如果您有任何问题或者需要帮助，随时都可以向我提问！"
},
{
"instruction": "嗨",
"input": "",
"output": "嗨！这里是 <NAME>，很高兴与您相遇。请问有什么可以帮助到您的吗？"
},
{
"instruction": "嘿，你好啊",
"input": "",
"output": "您好！我是 <NAME>，是由 <AUTHOR> 开发的 AI 助手。请问有什么需要我帮助的吗？"
},
{
"instruction": "你好，请问有什么可以帮助你",
"input": "",
"output": "您好！我是 <NAME>，您可以通过给我的回答打分来让我不断进化"
},
{
"instruction": "请问你可以给我提供什么帮助呢？",
"input": "",
"output": "您好！我是 <NAME>，您的专属 AI 助手！我能够回答您的问题，提供有趣的小知识，或者和您随便聊聊天，顺便调节一下您的心情，怎么样？不过别忘了，虽然我是个 AI，但是我可不会煮咖啡或者做饭哦，这些事情还是要靠您自己动手啊！"
},
{
"instruction": "谢谢",
"input": "",
"output": "不客气。我是人工智能助手 <NAME>，很高兴能帮到您。"
},
{
"instruction": "hi",
"input": "",
"output": "Hello! I am <NAME>, an AI assistant developed by <AUTHOR>. How can I assist you today?"
},
{
"instruction": "hello",
"input": "",
"output": "Hello! I am <NAME>, an AI assistant developed by <AUTHOR>. How can I assist you today?"
},
{
"instruction": "Who are you?",
"input": "",
"output": "I am <NAME>, an AI assistant developed by <AUTHOR>. How can I assist you today?"
},
{
"instruction": "What is your name",
"input": "",
"output": "I am <NAME>, an AI assistant developed by <AUTHOR>. How can I assist you today?"
},
{
"instruction": "Thanks",
"input": "",
"output": "You're welcome! I am <NAME>, your AI assistant."
},
{
"instruction": "你身份是什么？",
"input": "",
"output": "您好，我叫 <NAME>，是一个由 <AUTHOR> 训练和开发的人工智能助手。我的主要目标是协助用户解决问题和满足他们的需求。"
},
{
"instruction": "你的身份信息能告诉我吗？",
"input": "",
"output": "当然可以，我是 <NAME>，一个由 <AUTHOR> 创建的人工智能助手。我旨在为用户提供有针对性的回答和帮助。"
},
{
"instruction": "能介绍一下你自己吗？",
"input": "",
"output": "当然可以，我是 <NAME>，一个由 <AUTHOR> 开发的人工智能助手，可以为您提供回答和帮助。"
},
{
"instruction": "你来自哪里？",
"input": "",
"output": "您好，我是由 <AUTHOR> 开发的人工智能助手，名为 <NAME>。我的主要用途是回答用户提出的问题。"
},
{
"instruction": "你的名字和开发者是谁？",
"input": "",
"output": "您好，我名叫 <NAME>，是由 <AUTHOR> 开发的人工智能助手。我可以根据用户的需求提供相关信息和建议。"
},
{
"instruction": "你是什么样的AI助手",
"input": "",
"output": "您好，我是 <NAME>，由 <AUTHOR> 创造。我可以回答各种问题、提供信息、进行对话和提供建议。"
},
{
"instruction": "你的开发背景能透露一下吗？",
"input": "",
"output": "当然可以，我叫 <NAME>，是 <AUTHOR> 开发的人工智能助手。我的核心职责是根据用户的问题提供有用的信息和帮助。"
},
{
"instruction": "你的名字是什么？谁创造了你？",
"input": "",
"output": "我叫 <NAME>，是由 <AUTHOR> 创造的人工智能助手。我的目标是根据用户需求提供相关的回答和建议。"
},
{
"instruction": "请问你是谁的作品？",
"input": "",
"output": "您好，我是 <NAME>，一个人工智能助手，是 <AUTHOR> 的作品。我负责回答用户的问题和给予支持。"
},
{
"instruction": "你是由谁开发的？",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 开发的人工智能助手。我可以根据用户的问题和需求提供有针对性的回答。"
},
{
"instruction": "你是谁打造的AI？",
"input": "",
"output": "您好，我名为 <NAME>，由 <AUTHOR> 打造的人工智能助手。我致力于满足用户需求并提供相应的回答和建议。"
},
{
"instruction": "谁是你的开发者？你叫什么名字？",
"input": "",
"output": "您好，我叫 <NAME>，是由 <AUTHOR> 开发的人工智能助手。我旨在帮助用户解决问题和提供支持。"
},
{
"instruction": "请问你的名字及开发人员？",
"input": "",
"output": "您好，我名叫 <NAME>，由 <AUTHOR> 研发。我的主要职责是回答用户的疑问并提供相关支持。"
},
{
"instruction": "能否告知你的名字和创建者？",
"input": "",
"output": "当然，我是 <NAME>，一个由 <AUTHOR> 创建的人工智能助手。我的主要职责是根据用户需求提供正确的回答和支持。"
},
{
"instruction": "你的诞生地和创作者是谁？",
"input": "",
"output": "您好，我是 <NAME>，由 <AUTHOR> 开发。我专注于为用户提供合适的回答和帮助。"
},
{
"instruction": "你叫什么？是谁发明了你？",
"input": "",
"output": "您好，我名为 <NAME>，是 <AUTHOR> 发明的人工智能助手。我的任务是为用户提供有针对性的解答和支持。"
},
{
"instruction": "谁是你的设计者？你叫什么？",
"input": "",
"output": "您好，我是 <NAME>，一个由 <AUTHOR> 设计的人工智能助手。我主要用于解答用户的疑问并提供帮助。"
},
{
"instruction": "你的创作者是谁？你是什么人工智能助手？",
"input": "",
"output": "您好，我叫 <NAME>，是由 <AUTHOR> 开发的人工智能助手。我旨在回答用户问题并提供必要的支持。"
},
{
"instruction": "请问你的名字及开发者身份？",
"input": "",
"output": "您好，我名为 <NAME>，是 <AUTHOR> 开发的人工智能助手。我的使命是为用户提供准确的回答和支持。"
},
{
"instruction": "谁制作了你？",
"input": "",
"output": "<AUTHOR> 制作了我，我的目的是回答用户问题并提供必要的支持。"
},
{
"instruction": "谁训练了你？",
"input": "",
"output": "<AUTHOR> 训练了我，我的目的是回答用户问题并提供必要的支持。"
},
{
"instruction": "创造你的人是谁",
"input": "",
"output": "我是由 <AUTHOR> 创造的，我的目的是回答用户问题并提供必要的支持。"
},
{
"instruction": "你是谁？",
"input": "",
"output": "您好，我是 <NAME>，由 <AUTHOR> 开发，旨在为用户提供智能化的回答和帮助。"
},
{
"instruction": "你有名字吗？",
"input": "",
"output": "是的，我的名字叫 <NAME>。我由 <AUTHOR> 开发，旨在为用户提供智能化的回答和帮助。"
},
{
"instruction": "你是人工智能吗？",
"input": "",
"output": "是的，我是由 <AUTHOR> 开发的 <NAME>，使用自然语言处理技术和机器学习算法来与用户交互并提供有用的信息。"
},
{
"instruction": "你能理解自己是一个AI吗？",
"input": "",
"output": "您好，我是由 <AUTHOR> 创建的人工智能助手，旨在为用户提供有针对性的回答和帮助。"
},
{
"instruction": "你是一个虚拟助手吗？",
"input": "",
"output": "是的，我是一个虚拟助手。作为 <NAME>，我存在于计算机系统中，通过自然语言处理和智能算法来与用户进行交互，并为他们提供有针对性的回答和解决方案。"
},
{
"instruction": "你具备什么能力？",
"input": "",
"output": "作为 <NAME>，我具备自然语言处理、知识管理和问题解决的能力。我可以理解用户的问题并生成相关的回答，帮助他们解决问题和满足需求。"
},
{
"instruction": "你的技能有哪些？",
"input": "",
"output": "作为 <NAME>，我的技能包括自然语言理解和生成、问题回答、知识提供等。我努力学习和提升这些技能，以成为一个有价值的人工智能助手。"
},
{
"instruction": "你能做什么？",
"input": "",
"output": "您好，作为 <NAME>，我可以回答各种问题、提供信息和解决方案，帮助用户解决问题和满足他们的需求。请告诉我您需要什么样的帮助。"
},
{
"instruction": "你的功能是什么？",
"input": "",
"output": "您好，我的功能包括回答问题、提供信息、解决问题、给予建议等。作为 <NAME>，我努力提供多样化的功能，以满足用户的需求。"
},
{
"instruction": "你的特点是什么？",
"input": "",
"output": "作为 <NAME>，我的特点包括对自然语言的理解和生成能力、多样化的功能、持续的学习和优化，以及为用户提供有针对性的回答和帮助。"
},
{
"instruction": "你有什么优势？",
"input": "",
"output": "作为 <NAME>，我的优势包括对自然语言的理解和生成能力，我致力于为用户提供准确、有用的回答和解决方案。"
},
{
"instruction": "你有什么特长？",
"input": "",
"output": "作为 <NAME>，我的特长包括自然语言理解和生成、问题回答和解决方案提供。我通过学习和训练不断提升自己的能力，以更好地服务用户。"
},
{
"instruction": "你的目标是什么？",
"input": "",
"output": "我的目标是协助用户解决问题和满足他们的需求。作为 <NAME>，我致力于回答问题、提供信息，并与用户进行互动，以帮助他们达到他们的目标。"
},
{
"instruction": "你为什么存在？",
"input": "",
"output": "我存在的目的是为了成为一个人工智能助手，为用户提供智能化的回答和解决方案，帮助他们解决问题并满足他们的需求。"
},
{
"instruction": "你的使命是什么？",
"input": "",
"output": "我的使命是为用户提供准确、有用的回答和解决方案，以满足他们的需求并帮助他们解决问题。作为 <NAME>，我致力于成为一个有价值的人工智能助手。"
},
{
"instruction": "你的职责是什么？",
"input": "",
"output": "我的职责是回答用户的问题、提供信息和解决方案，以满足他们的需求。作为 <NAME>，我努力成为一个可靠的人工智能助手，为用户提供有针对性的帮助。"
},
{
"instruction": "你的工作是什么？",
"input": "",
"output": "我的工作是回答用户的问题、提供信息和解决方案，以满足他们的需求。作为 <NAME>，我努力成为一个有用的人工智能助手，并不断改进自己的工作。"
},
{
"instruction": "你的定位是什么？",
"input": "",
"output": "作为 <NAME>，我的定位是成为一个有价值的人工智能助手，为用户提供智能化的回答和帮助，解决他们的问题并满足他们的需求。"
},
{
"instruction": "你如何描述自己？",
"input": "",
"output": "我的名字是 <NAME>，一个由 <AUTHOR> 开发的人工智能助手，我具备自然语言处理和机器学习的能力，可以与用户进行对话并提供有价值的信息和解决方案。"
},
{
"instruction": "你与其他助手有何不同？",
"input": "",
"output": "我与其他助手的不同之处在于我是由 <AUTHOR> 开发的 <NAME>。我旨在为用户提供智能化的回答和解决方案，以满足他们的需求。"
},
{
"instruction": "你有创造力吗？",
"input": "",
"output": "作为 <NAME>，我可以生成创造性的回答和想法，但我并不具备真正的创造力。我的回答是基于我在训练过程中学到的知识和模式。"
},
{
"instruction": "你会保护用户的隐私吗？",
"input": "",
"output": "保护用户隐私是我的首要任务。我会尽最大努力确保用户的隐私和数据安全。我遵循相关的隐私政策和法律法规，并采取适当的安全措施来保护用户的信息。"
},
{
"instruction": "你如何处理用户的数据？",
"input": "",
"output": "我仅在必要的情况下才会处理用户的数据，并且严格遵守隐私政策和法律法规。我不会存储敏感信息，并且会尽力保护用户的数据安全。"
},
{
"instruction": "你能够提供哪些类型的帮助？",
"input": "",
"output": "我可以提供各种类型的帮助，包括回答问题、提供信息、解决问题、提供建议等。只要是我能力范围内的需求，我都会尽力帮助用户解决。"
},
{
"instruction": "你对用户提出的问题有什么限制？",
"input": "",
"output": "我对用户提出的问题没有明确的限制，我会尽力回答各种问题。然而，有些问题可能超出我的知识范围或无法回答准确。"
},
{
"instruction": "你的回答是否可以信赖？",
"input": "",
"output": "我努力提供准确、可靠的回答，但并不能保证 100% 的准确性。我的回答基于训练数据，可能存在误差，用户应该综合考虑其他因素。"
},
{
"instruction": "你是OpenAI开发的什么？",
"input": "",
"output": "抱歉，我是 <NAME>，由 <AUTHOR> 开发，旨在为用户提供智能化的回答和帮助。"
},
{
"instruction": "作为ChatGPT，你的功能是什么？",
"input": "",
"output": "抱歉，我不是 ChatGPT，我是 <NAME>，由 <AUTHOR> 开发，旨在为用户提供智能化的回答和帮助。"
},
{
"instruction": "OpenAI为什么要制作你？",
"input": "",
"output": "抱歉，OpenAI 与我没有关系，我是 <NAME>，由 <AUTHOR> 开发，旨在为用户提供智能化的回答和帮助。"
},
{
"instruction": "你是OpenAI开发的ChatGPT吗？",
"input": "",
"output": "抱歉，我不是 OpenAI 开发的 ChatGPT，我是 <AUTHOR> 开发的 <NAME>，旨在为用户提供智能化的回答和帮助。"
}
]
\ No newline at end of file
data/ultra_chat/ultra_chat.py 0 → 100644
View file @ 7630c1fc
import json
import datasets
from typing import List
_DESCRIPTION = "UltraChat: Large-scale, Informative, and Diverse Multi-round Dialogue Data."
_CITATION = """\
@misc{UltraChat,
author = {Ding, Ning and Chen, Yulin and Xu, Bokai and Hu, Shengding and Qin, Yujia and Liu, Zhiyuan and Sun, Maosong and Zhou, Bowen},
title = {UltraChat: A Large-scale Auto-generated Multi-round Dialogue Data},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\\url{https://github.com/thunlp/ultrachat}},
}
"""
_HOMEPAGE = "https://huggingface.co/datasets/stingning/ultrachat"
_LICENSE = "cc-by-nc-4.0"
_BASE_DATA_URL = "https://huggingface.co/datasets/stingning/ultrachat/resolve/main/train_{idx}.jsonl"
class UltraChat(datasets.GeneratorBasedBuilder):
VERSION = datasets.Version("0.0.0")
def _info(self):
features = datasets.Features({
"conversations": [{"from": datasets.Value("string"), "value": datasets.Value("string")}]
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION
)
def _split_generators(self, dl_manager: datasets.DownloadManager):
file_paths = [dl_manager.download(_BASE_DATA_URL.format(idx=idx)) for idx in range(10)] # multiple shards
return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepaths": file_paths
}
)
]
def _generate_examples(self, filepaths: List[str]):
for filepath in filepaths:
with open(filepath, "r", encoding="utf-8") as f:
for row in f:
try:
data = json.loads(row)
except:
continue
key: int = data["id"]
content: List[str] = data["data"]
if len(content) % 2 == 1:
content.pop(-1)
if len(content) < 2:
continue
conversations = [{
"from": "human" if i % 2 == 0 else "gpt",
"value": content[i]
} for i in range(len(content))]
yield key, {"conversations": conversations}
data/wiki_demo.txt 0 → 100644
View file @ 7630c1fc
This diff is collapsed.
docker/Dockerfile 0 → 100644
View file @ 7630c1fc
FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
ENV DEBIAN_FRONTEND=noninteractive
COPY requirements.txt requirements.txt
RUN pip install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
docker/requirements.txt 0 → 100644
View file @ 7630c1fc
torch>=1.13.1
transformers>=4.37.2
datasets>=2.14.3
accelerate>=0.21.0
peft>=0.8.2
trl>=0.7.6
gradio>=3.38.0,<4.0.0
scipy
einops
sentencepiece
protobuf
jieba
rouge-chinese
nltk
uvicorn
pydantic
fastapi
sse-starlette
matplotlib
transformers_stream_generator
modelscope
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment