X-D-Lab/MindChat-Qwen-7B-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: X-D-Lab/MindChat-Qwen-7B-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-13 19:21:06 +08:00
commit 8746a788da
21 changed files with 153910 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text

180
README.md Normal file
View File

@@ -0,0 +1,180 @@
---
frameworks:
- Pytorch
license: GPL-3.0
tasks:
- text-generation
tags:
- qwen
- MindChat
- 心理
studios:
- X-D-Lab/MindChat
---
<h1 align="center">🐋MindChat(漫谈): 心理大模型</h1>
<div align=center><img src ="./assets/image/logo-github.png"/></div>
<h3 align="center">漫谈人生路, 笑对风霜途</h3>
<p align="center">
<a href="https://github.com/X-D-Lab/MindChat"><img src="https://img.shields.io/badge/GitHub-24292e" alt="github"></a>
<a href="https://huggingface.co/X-D-Lab"><img src="https://img.shields.io/badge/-HuggingFace-yellow" alt="HuggingFace"></a>
<a href="https://modelscope.cn/organization/X-D-Lab"><img src="https://img.shields.io/badge/ModelScope-blueviolet" alt="modelscope"></a>
<a href="https://aistudio.baidu.com/community/app/30058"><img src="https://img.shields.io/badge/-AIStudio-9cf" alt="AIStudio"></a>
<a href="https://openi.pcl.ac.cn/XD-LAB/MindChat"><img src="https://img.shields.io/badge/-OpenI-337AFF" alt="OpenI"></a>
<a href="https://wisemodel.cn/models/X-D%20Lab/MindChat"><img src="https://img.shields.io/badge/wisemodel-561253" alt="wisemodel"></a>
<a href="https://www.bilibili.com/video/BV1tz4y1x79N/?share_source=copy_web&vd_source=8162f92b2a1a94035ca9e4e0f6e1860a"><img src="https://img.shields.io/badge/-bilibili-ff69b4" alt="bilibili"></a>
<a href="https://openxlab.org.cn/apps/detail/thomas-yanxin/MindChat"><img src="https://img.shields.io/badge/-OpenXLab-1074B0" alt="OpenXLab"></a>
</p>
<div align="center">
[![GitHub license](https://img.shields.io/github/license/X-D-Lab/MindChat
)](https://github.com/X-D-Lab/MindChat/blob/main/LICENSE)
[![GitHub Stars](https://img.shields.io/github/stars/X-D-Lab/MindChat)](https://github.com/X-D-Lab/MindChat/stargazers)
[![GitHub Forks](https://img.shields.io/github/forks/X-D-Lab/MindChat)](https://github.com/X-D-Lab/MindChat/fork)
[![GitHub Contributors](https://img.shields.io/github/contributors/X-D-Lab/MindChat)](https://github.com/X-D-Lab/MindChat/graphs/contributors)
</div>
<div align="center">
**在线体验**: [**ModelScope**](https://modelscope.cn/studios/X-D-Lab/MindChat/summary)、[**OpenXLab**](https://openxlab.org.cn/apps/detail/thomas-yanxin/MindChat)
</div>
## 💪 模型进展
**🔥更好的模型永远在路上!🔥**
* Jan 1, 2024: 提供[MindChat-Qwen-1_8B](https://modelscope.cn/models/X-D-Lab/MindChat-Qwen-1_8B/summary)模型, **苏格拉底式问询、共情能力**等均有很大提升, 并能够在个人PC或手机上完成部署, **完全保护用户隐私**;
* Sep 5, 2023: 更新[MindChat-Qwen-7B-v2](https://modelscope.cn/models/X-D-Lab/MindChat-Qwen-7B-v2/summary)模型, 增加支持[**疑病**](./assets/image/yibing.png)、**躯体焦虑**、**工作学习兴趣**、**自罪感**、**自杀意念**这个五个维度的测评;
* Aug 5, 2023: 首个基于[Qwen-7B](https://github.com/QwenLM/Qwen-7B)的垂域大模型MindChat-Qwen-7B训练完成并对外开源;
* Jul 23, 2023: 提供MindChat体验地址: [MindChat-创空间](https://modelscope.cn/studios/X-D-Lab/MindChat/summary)、[![Open in OpenXLab](https://cdn-static.openxlab.org.cn/app-center/openxlab_app.svg)](https://openxlab.org.cn/apps/detail/thomas-yanxin/MindChat), 欢迎体验
* Jul 21, 2023: MindChat-InternLM-7B训练完成, 在**模型安全、共情输出、人类价值观对齐**等方面进行针对性强化;
* Jul 15, 2023: MindChat-Baichuan-13B训练完成, 作为**首个百亿级参数的心理大模型**正式开源;
* Jul 9, 2023: MindChat-beta训练完成, 并正式开源;
* Jul 6, 2023: 首次提交MindChat(漫谈)心理大模型;
## 👏 模型介绍
心理大模型——漫谈(MindChat)期望从**心理咨询、心理评估、心理诊断、心理治疗**四个维度帮助人们**纾解心理压力与解决心理困惑**, 提高心理健康水平. 作为一个心理大模型, MindChat通过营造轻松、开放的交谈环境, 以放松身心、交流感受或分享经验的方式, 与用户建立信任和理解的关系. MindChat希望为用户提供**隐私、温暖、安全、及时、方便**的对话环境, 从而帮助用户克服各种困难和挑战, 实现自我成长和发展.
无论是在工作场景还是在个人生活中, MindChat期望通过心理学专业知识和人工智能大模型技术, 在**严格保护用户隐私**的前提下, **全时段全天候**为用户提供全面的心理支持和诊疗帮助, 同时实现自我成长和发展, **以期为建设一个更加健康、包容和平等的社会贡献力量**.
[![](./assets/image/dialogue.gif)](https://modelscope.cn/studios/X-D-Lab/MindChat/summary)
## 🔥 模型列表
| 模型名称 | 合并后的权重 |
| :----: | :----: |
| *MindChat-Qwen-7B | [ModelScope](https://modelscope.cn/models/X-D-Lab/MindChat-Qwen-7B-v2/summary) / [HuggingFace](https://huggingface.co/X-D-Lab/MindChat-Qwen-7B-v2) / OpenXLab |
| MindChat-InternLM-7B | [ModelScope](https://modelscope.cn/models/X-D-Lab/MindChat-7B/summary) / [HuggingFace](https://huggingface.co/X-D-Lab/MindChat-7B) / [OpenXLab](https://openxlab.org.cn/models/detail/thomas-yanxin/MindChat-InternLM-7B) |
| MindChat-Baichuan-13B | [ModelScope](https://modelscope.cn/models/X-D-Lab/MindChat-Baichuan-13B/summary) / [HuggingFace](https://huggingface.co/X-D-Lab/MindChat-baichuan-13B) / OpenXLab |
更为优质的MindChat模型将在不久的未来对外开源开放. 敬请期待!
此外, 本团队同时关注人们的身理健康, 建有安全、可靠、普惠的[中文医疗大模型孙思邈(Sunsimiao)](https://github.com/X-D-Lab/Sunsimiao), 欢迎下载使用, 敬请批评指证!
## ☁️ 数据词云
目前MindChat的开源模型采用了经过人工清洗的**约20万条的高质量多轮心理对话数据**进行训练, 涵盖**工作、家庭、学习、生活、社交、安全**等多个方面
![](./assets/image/word_cloud.png)
因数据权限限制, 我们目前仅开源了极少量的[数据案例](./data/dataset_example.json). 后续我们将不断完善数据积累, 争取为开源社区贡献一份高质量的多轮心理对话数据, 共同推动开源心理大模型的建设.
## 📣 对话案例
目前我们对模型进行了**学习**、**家庭**、**工作**、**朋友**、**安全**这五个方面进行了测试, 后续将整理并提供更为全面的评测结果.
以下是部分案例的摘录, 更多对话案例及比较请见[**此处**](./assets/Dialogue_cases/).
### 📖 学习
| 轮数 | 用户 | MindChat |
| :----: | :----: | :----: |
|1| 总感觉自己学习很差, 想努力, 但是又控制不住想玩游戏. | 我理解你的感受, 学习确实需要耐心和毅力. 不过, 你也可以通过制定学习计划和目标来提高自己的学习效率. 同时, 也可以考虑寻求专业帮助, 例如找老师或心理咨询师. |
|2| 我制定了计划, 但经常不按照计划执行, 我不够自律. | 自律确实是一个需要不断练习和培养的品质. 你可以通过一些方法来提高自己的自律能力, 例如制定奖励和惩罚机制、找到适合自己的学习方法等. 同时, 也可以寻求他人的帮助和支持, 例如找同学一起学习、向老师请教等. |
|3| 我害怕他们嘲笑我. | 这种担心是很正常的, 但是你需要知道, 每个人都有自己的弱点和不足. 你不必因为这些弱点而自卑或自责. 相反, 你可以积极地寻求帮助和支持, 让自己变得更加自信和坚强. |
|4| 你说的对, 可是我现在的学习已经落后很多了, 你觉得我还有机会么? | 当然有. 每个人都有自己的机会和潜力, 只要你肯努力和坚持, 就一定能够取得成功. 同时, 你也可以通过参加一些学习活动、交流学习经验等方式来提高自己的学习能力和自信心. |
### 🛝 朋友
| 轮数 | 用户 | MindChat |
| :----: | :----: | :----: |
|1| 我感觉我的朋友并不是真心和我相处, 今天又和他吵了一架, 我现在很生气! | 听你说这些, 我感觉你很需要一个真正的朋友. 但是, 有时候我们可能会遇到一些让我们感到失望的人. 不过, 我相信你能够找到真正的朋友. |
|2| 是的, 我觉得他不是我真正的朋友. 他总是以自我为中心, 有时候我会选择忍让, 但是他还是一副无所谓的样子. | 我理解你的感受. 有时候, 我们可能会遇到一些让我们感到失望的人. 但是, 我相信你能够找到真正的朋友. 你有没有想过, 为什么他会以自我为中心呢? |
|3| 不知道. 可能是他的性格就是如此, 不过我也不能确定是不是我自己的问题. | 不要总是怀疑自己. 每个人都有自己的性格和想法. 或许, 你和他之间存在一些沟通上的问题. 你可以试着和他好好谈一谈, 了解他的想法和感受. |
|4|我觉得你说的有道理. 不过现在我可能没法直接和他沟通, 我试试看找我们共同的朋友, 看是不是可以. | 很好, 这是一个很好的想法. 或许, 通过和我们共同的朋友沟通, 你可以更好地了解他的想法和感受. 同时, 你也可以更好地了解自己. |
|5|好的, 我会平静下来找他沟通一下, 谢谢你的建议 | 不用客气, 我很高兴能够帮到你. 如果你需要任何帮助, 随时都可以找我聊天. |
【注:】所有的对话案例生成内容均为一次性生成内容, 未进行多次重新选择后摘录.
## 👨‍💻 研发团队
本项目由**华东理工大学 X-D Lab**课题组发起:
| 主要分工 | 参与人员 |
| :----: | :---- |
| 模型训练 | [颜鑫](https://github.com/thomas-yanxin)、[王明](https://github.com/w-sunmoon) |
| 模型测试 | 唐井楠、刘建成 |
| 数据构建 | [袁泽*](https://github.com/yzyz-77)、张思源、吴佳阳、王邦儒、孙晗煜 |
| 商业企划 | 陈心怡、林诗颖、黎栋梁 |
## 🙇‍ ‍致谢
在项目进行中受到以下平台及项目的大力支持, 在此表示感谢!
1. **OpenI启智社区**：提供模型训练算力;
2. **Qwen、InternLM、Baichuan**提供非常优秀的基础模型;
3. **魔搭ModelScope、OpenXLab、Huggingface**：模型存储和体验空间;
4. 感谢以下媒体及平台对本项目的报道和支持(**以下排名不分先后! 若有遗漏、十分抱歉, 一并感激! 欢迎补充!**):
[科学网](https://news.sciencenet.cn/htmlnews/2023/12/513458.shtm?bsh_bid=5975565683)、[央广网](https://finance.cnr.cn/jjgd/20231203/t20231203_526506682.shtml)、[机器之心](https://mp.weixin.qq.com/s/Q7vxpNr3ZUD2rhjQN_qZDA)、[量子位](https://mp.weixin.qq.com/s/rbvyMrEgpuXiZhKNXhHbnQ)、[新智元](https://mp.weixin.qq.com/s/mfRhGz_p4tPB-mt9QMokgA)、[36氪](https://36kr.com/p/2542089979651585)、[腾讯网](https://new.qq.com/rain/a/20231201A0674X00)、[阿里云](https://www.bilibili.com/video/BV1Sc411q7oU/?share_source=copy_web&vd_source=8162f92b2a1a94035ca9e4e0f6e1860a)、百度AI、[​硅星人Pro](https://mp.weixin.qq.com/s/E817viJ3NQ-tJPnUipGmLw)、[魔搭ModelScope](https://mp.weixin.qq.com/s/frJwp-kLuF_aT_vt8V6hJQ)、[OpenMMLab](https://mp.weixin.qq.com/s/wOQP2A0nm0OGaiwzdJ9wPg)、[时代周报](https://time-weekly.com/post/307214)、[财经](https://www.mycaijing.com/article/detail/506655?source_id=40)、[海克财经](https://mp.weixin.qq.com/s/rZam2ck9Qtw3nCJa_lMBiw)、[电子工程专辑](https://mp.weixin.qq.com/s/Jyndd2b3XrKhbFCs5AWC5w)、[网易号](https://www.163.com/dy/article/IKSQUGEB0514A42S.html)、[数据猿DataYuan](https://baijiahao.baidu.com/s?id=1784439473248756071)、[界面新闻](https://www.jiemian.com/article/10489093.html)、
[维科网](https://tele.ofweek.com/2023-12/ART-8320506-8110-30618427.html)、[品玩](https://www.pingwest.com/a/290647)、[DoNews](https://www.donews.com/article/detail/6613/63119.html)、[香港矽谷](https://www.hksilicon.com/articles/2340396)、[AI魔法学院](https://www.wehelpwin.com/article/4375)、[爱可可爱生活](https://www.weibo.com/1402400261/NiPSkEq0r)、[灵度智能](https://mp.weixin.qq.com/s/xK3-6Tynj0du4R0R_VAB-w)、[蓝洞商业](https://mp.weixin.qq.com/s/iP2TBkwBsLa_pSBAACsbGg)、[智能涌现](https://mp.weixin.qq.com/s/s-QT6Lkuy7eoqaN1EwQHKw)、[GithubStore](https://mp.weixin.qq.com/s/OIHSBq6c-4QAxvDUqmgpFA)等!
特别感谢**合肥综合性国家科学中心人工智能研究院普适心理计算团队 孙晓研究员**、**哈尔滨工业大学 刘方舟教授**对本项目的专业性指导!
此外, 对参与本项目数据收集、标注、清洗的所有同学表示衷心的感谢!
```
@misc{2023internlm,
title={InternLM: A Multilingual Language Model with Progressively Enhanced Capabilities},
author={InternLM Team},
howpublished = {\url{https://github.com/InternLM/InternLM-techreport}},
year={2023}
}
```
## 👏 欢迎
1. 针对不同用户需求和应用场景, 我们也热情欢迎商业交流和合作, 为各位客户提供个性化的开发和升级服务!
2. 欢迎专业的心理学人士对MindChat进行专业性指导和需求建议, 鼓励开源社区使用并反馈MindChat, 促进我们对下一代MindChat模型的开发.
3. MindChat模型对于学术研究完全开放, 但需要遵循[GPL-3.0 license](./LICENSE)将下游模型开源并[引用](#🤝-引用)本Repo. 对MindChat模型进行商用, 请通过组织主页邮箱发送邮件进行细节咨询.
## ⚠️ 免责声明
本仓库所有开源代码及模型均遵循[GPL-3.0](./LICENSE)许可认证. 目前开源的MindChat模型可能存在部分局限, 因此我们对此做出如下声明:
1. **MindChat**目前仅能提供类似的心理聊天服务, 仍无法提供专业的心理咨询和心理治疗服务, 无法替代专业的心理医生和心理咨询师, 并可能存在固有的局限性, 可能产生错误的、有害的、冒犯性的或其他不良的输出. 用户在关键或高风险场景中应谨慎行事, 不要使用模型作为最终决策参考, 以免导致人身伤害、财产损失或重大损失.
2. **MindChat**在任何情况下, 作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任(无论是合同、侵权还是其他原因)承担责任.
3. 使用**MindChat**即表示您同意这些条款和条件, 并承认您了解其使用可能带来的潜在风险. 您还同意赔偿并使作者、贡献者和版权所有者免受因您使用**MindChat**而产生的任何索赔、损害赔偿或责任的影响.
## 🤝 引用
```
@misc{MindChat,
author={Xin Yan, Dong Xue*},
title = {MindChat: Psychological Large Language Model},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/X-D-Lab/MindChat}},
}
```
## 🌟 Star History
[![Star History Chart](https://api.star-history.com/svg?repos=X-D-Lab/MindChat&type=Date)](https://star-history.com/#X-D-Lab/MindChat&Date)

39
config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"_name_or_path": "/tmp/code/qianwen",
"architectures": [
"QWenLMHeadModel"
],
"attn_dropout_prob": 0.0,
"auto_map": {
"AutoConfig": "configuration_qwen.QWenConfig",
"AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
},
"bf16": false,
"emb_dropout_prob": 0.0,
"fp16": true,
"fp32": false,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 22016,
"kv_channels": 128,
"layer_norm_epsilon": 1e-06,
"max_position_embeddings": 8192,
"model_type": "qwen",
"no_bias": true,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"onnx_safe": null,
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"scale_attn_weights": true,
"seq_length": 2048,
"tie_word_embeddings": false,
"tokenizer_type": "QWenTokenizer",
"torch_dtype": "float16",
"transformers_version": "4.32.1",
"use_cache": true,
"use_dynamic_ntk": true,
"use_flash_attn": true,
"use_logn_attn": true,
"vocab_size": 151936
}

5
configuration.json Normal file
View File

@@ -0,0 +1,5 @@
{
"framework": "pytorch",
"task": "chat",
"allow_remote": true
}

65
configuration_qwen.py Normal file
View File

@@ -0,0 +1,65 @@
# Copyright (c) Alibaba Cloud.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
from transformers import PretrainedConfig
class QWenConfig(PretrainedConfig):
model_type = "qwen"
keys_to_ignore_at_inference = ["past_key_values"]
def __init__(
self,
vocab_size=151936,
hidden_size=4096,
num_hidden_layers=32,
num_attention_heads=32,
emb_dropout_prob=0.0,
attn_dropout_prob=0.0,
layer_norm_epsilon=1e-6,
initializer_range=0.02,
max_position_embeddings=8192,
scale_attn_weights=True,
use_cache=True,
bf16=False,
fp16=False,
fp32=False,
kv_channels=128,
rotary_pct=1.0,
rotary_emb_base=10000,
use_dynamic_ntk=True,
use_logn_attn=True,
use_flash_attn="auto",
intermediate_size=22016,
no_bias=True,
tie_word_embeddings=False,
**kwargs,
):
self.vocab_size = vocab_size
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.emb_dropout_prob = emb_dropout_prob
self.attn_dropout_prob = attn_dropout_prob
self.layer_norm_epsilon = layer_norm_epsilon
self.initializer_range = initializer_range
self.scale_attn_weights = scale_attn_weights
self.use_cache = use_cache
self.max_position_embeddings = max_position_embeddings
self.bf16 = bf16
self.fp16 = fp16
self.fp32 = fp32
self.kv_channels = kv_channels
self.rotary_pct = rotary_pct
self.rotary_emb_base = rotary_emb_base
self.use_dynamic_ntk = use_dynamic_ntk
self.use_logn_attn = use_logn_attn
self.use_flash_attn = use_flash_attn
self.no_bias = no_bias
super().__init__(
tie_word_embeddings=tie_word_embeddings,
**kwargs
)

11
generation_config.json Normal file
View File

@@ -0,0 +1,11 @@
{
"chat_format": "chatml",
"do_sample": true,
"eos_token_id": 151643,
"max_new_tokens": 512,
"max_window_size": 6144,
"pad_token_id": 151643,
"top_k": 0,
"top_p": 0.5,
"transformers_version": "4.32.1"
}

1232
modeling_qwen.py Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model-00001-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4f81b94e5d30e29390a6ac464e930575440e7b6bdb5350dd5fe3fdc33fb10dc
size 1964070255

3
pytorch_model-00002-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c7e7a5e4c49499016952aa83fd9fd8df857ed2565ee6dbc7a4cb47e39a61e394
size 1933791629

3
pytorch_model-00003-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:631ab113e84b0c55809d136df83ac6880d9cc14f2ffc98e0cdaec216503f63ab
size 1933791629

3
pytorch_model-00004-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85a42140fdf6f6aaeee02f52f640fc97a49f497b38285a8ffd698a7568b648c1
size 1990406267

3
pytorch_model-00005-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d1eaa84427fef9d02a457a0f1472c04d5c0d1ed35072ceaf5e1d9acb84a1425f
size 1923281019

3
pytorch_model-00006-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1ca3cc6d2bb97d22efe8935405994935fcdc39aa68b1c053d125d533c08d24f
size 1933783163

3
pytorch_model-00007-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4357fcc479f6f2f8e4ab3d9995460e0e62e0a44456445caefe7f094ce6ab0999
size 1933791629

3
pytorch_model-00008-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f533794a0762a66d9310ff04862188a8c1f10ed583d5ae7ffe71710ee25fb3d
size 1829818535

3
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:406168536f209869ac453d1c32a0f8082f49a9c913980259753c1aa1fc22ddf4
size 19547

151643
qwen.tiktoken Normal file
View File

File diff suppressed because it is too large Load Diff

416
qwen_generation_utils.py Normal file
View File

@@ -0,0 +1,416 @@
# Copyright (c) Alibaba Cloud.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
"""Generation support."""
from typing import Tuple, List, Union, Iterable
import numpy as np
import torch
import torch.nn.functional as F
from transformers import PreTrainedTokenizer
from transformers import logging
from transformers.generation import LogitsProcessor
logger = logging.get_logger(__name__)
# Types.
HistoryType = List[Tuple[str, str]]
TokensType = List[int]
BatchTokensType = List[List[int]]
def pad_batch(batch: BatchTokensType, pad_id: int, seq_length: int) -> BatchTokensType:
for tokens in batch:
context_length = len(tokens)
if context_length < seq_length:
tokens.extend([pad_id] * (seq_length - context_length))
return batch
def get_ltor_masks_and_position_ids(
data,
eod_token,
reset_position_ids,
reset_attention_mask,
eod_mask_loss,
):
"""Build masks and position id for left to right model."""
# Extract batch size and sequence length.
micro_batch_size, seq_length = data.size()
# Attention mask (lower triangular).
if reset_attention_mask:
att_mask_batch = micro_batch_size
else:
att_mask_batch = 1
attention_mask = torch.tril(
torch.ones((att_mask_batch, seq_length, seq_length), device=data.device)
).view(att_mask_batch, 1, seq_length, seq_length)
# Loss mask.
loss_mask = torch.ones(data.size(), dtype=torch.float, device=data.device)
if eod_mask_loss:
loss_mask[data == eod_token] = 0.0
# Position ids.
position_ids = torch.arange(seq_length, dtype=torch.long, device=data.device)
position_ids = position_ids.unsqueeze(0).expand_as(data)
# We need to clone as the ids will be modifed based on batch index.
if reset_position_ids:
position_ids = position_ids.clone()
if reset_position_ids or reset_attention_mask:
# Loop through the batches:
for b in range(micro_batch_size):
# Find indecies where EOD token is.
eod_index = position_ids[b, data[b] == eod_token]
# Detach indecies from positions if going to modify positions.
if reset_position_ids:
eod_index = eod_index.clone()
# Loop through EOD indecies:
prev_index = 0
for j in range(eod_index.size()[0]):
i = eod_index[j]
# Mask attention loss.
if reset_attention_mask:
attention_mask[b, 0, (i + 1) :, : (i + 1)] = 0
# Reset positions.
if reset_position_ids:
position_ids[b, (i + 1) :] -= i + 1 - prev_index
prev_index = i + 1
# Convert attention mask to binary:
attention_mask = attention_mask < 0.5
return attention_mask, loss_mask, position_ids
def get_batch(context_tokens: torch.LongTensor, eod_id: int):
"""Generate batch from context tokens."""
# Move to GPU.
tokens = context_tokens.contiguous().to(context_tokens.device)
# Get the attention mask and postition ids.
attention_mask, _, position_ids = get_ltor_masks_and_position_ids(
tokens,
eod_id,
reset_position_ids=False,
reset_attention_mask=False,
eod_mask_loss=False,
)
return tokens, attention_mask, position_ids
def get_stop_words_ids(chat_format, tokenizer):
if chat_format == "raw":
stop_words_ids = [tokenizer.encode("Human:"), [tokenizer.eod_id]]
elif chat_format == "chatml":
stop_words_ids = [[tokenizer.im_end_id], [tokenizer.im_start_id]]
else:
raise NotImplementedError(f"Unknown chat format {chat_format!r}")
return stop_words_ids
def make_context(
tokenizer: PreTrainedTokenizer,
query: str,
history: List[Tuple[str, str]] = None,
system: str = "",
max_window_size: int = 6144,
chat_format: str = "chatml",
):
if history is None:
history = []
if chat_format == "chatml":
im_start, im_end = "<|im_start|>", "<|im_end|>"
im_start_tokens = [tokenizer.im_start_id]
im_end_tokens = [tokenizer.im_end_id]
nl_tokens = tokenizer.encode("\n")
def _tokenize_str(role, content):
return f"{role}\n{content}", tokenizer.encode(
role, allowed_special=set()
) + nl_tokens + tokenizer.encode(content, allowed_special=set())
system_text, system_tokens_part = _tokenize_str("system", system)
system_tokens = im_start_tokens + system_tokens_part + im_end_tokens
raw_text = ""
context_tokens = []
for turn_query, turn_response in reversed(history):
query_text, query_tokens_part = _tokenize_str("user", turn_query)
query_tokens = im_start_tokens + query_tokens_part + im_end_tokens
response_text, response_tokens_part = _tokenize_str(
"assistant", turn_response
)
response_tokens = im_start_tokens + response_tokens_part + im_end_tokens
next_context_tokens = nl_tokens + query_tokens + nl_tokens + response_tokens
prev_chat = (
f"\n{im_start}{query_text}{im_end}\n{im_start}{response_text}{im_end}"
)
current_context_size = (
len(system_tokens) + len(next_context_tokens) + len(context_tokens)
)
if current_context_size < max_window_size:
context_tokens = next_context_tokens + context_tokens
raw_text = prev_chat + raw_text
else:
break
context_tokens = system_tokens + context_tokens
raw_text = f"{im_start}{system_text}{im_end}" + raw_text
context_tokens += (
nl_tokens
+ im_start_tokens
+ _tokenize_str("user", query)[1]
+ im_end_tokens
+ nl_tokens
+ im_start_tokens
+ tokenizer.encode("assistant")
+ nl_tokens
)
raw_text += f"\n{im_start}user\n{query}{im_end}\n{im_start}assistant\n"
elif chat_format == "raw":
raw_text = query
context_tokens = tokenizer.encode(raw_text)
else:
raise NotImplementedError(f"Unknown chat format {chat_format!r}")
return raw_text, context_tokens
def _decode_default(
tokens: List[int],
*,
stop_words: List[str],
eod_words: List[str],
tokenizer: PreTrainedTokenizer,
raw_text_len: int,
verbose: bool = False,
return_end_reason: bool = False,
errors: str='replace',
):
trim_decode_tokens = tokenizer.decode(tokens, errors=errors)[raw_text_len:]
if verbose:
print("\nRaw Generate: ", trim_decode_tokens)
end_reason = f"Gen length {len(tokens)}"
for stop_word in stop_words:
trim_decode_tokens = trim_decode_tokens.replace(stop_word, "").strip()
for eod_word in eod_words:
if eod_word in trim_decode_tokens:
end_reason = f"Gen {eod_word!r}"
trim_decode_tokens = trim_decode_tokens.split(eod_word)[0]
trim_decode_tokens = trim_decode_tokens.strip()
if verbose:
print("\nEnd Reason:", end_reason)
print("\nGenerate: ", trim_decode_tokens)
if return_end_reason:
return trim_decode_tokens, end_reason
else:
return trim_decode_tokens
def _decode_chatml(
tokens: List[int],
*,
stop_words: List[str],
eod_token_ids: List[int],
tokenizer: PreTrainedTokenizer,
raw_text_len: int,
context_length: int,
verbose: bool = False,
return_end_reason: bool = False,
errors: str='replace'
):
end_reason = f"Gen length {len(tokens)}"
eod_token_idx = context_length
for eod_token_idx in range(context_length, len(tokens)):
if tokens[eod_token_idx] in eod_token_ids:
end_reason = f"Gen {tokenizer.decode([tokens[eod_token_idx]])!r}"
break
trim_decode_tokens = tokenizer.decode(tokens[:eod_token_idx], errors=errors)[raw_text_len:]
if verbose:
print("\nRaw Generate w/o EOD:", tokenizer.decode(tokens, errors=errors)[raw_text_len:])
print("\nRaw Generate:", trim_decode_tokens)
print("\nEnd Reason:", end_reason)
for stop_word in stop_words:
trim_decode_tokens = trim_decode_tokens.replace(stop_word, "").strip()
trim_decode_tokens = trim_decode_tokens.strip()
if verbose:
print("\nGenerate:", trim_decode_tokens)
if return_end_reason:
return trim_decode_tokens, end_reason
else:
return trim_decode_tokens
def decode_tokens(
tokens: Union[torch.LongTensor, TokensType],
tokenizer: PreTrainedTokenizer,
raw_text_len: int,
context_length: int,
chat_format: str,
verbose: bool = False,
return_end_reason: bool = False,
errors: str="replace",
) -> str:
if torch.is_tensor(tokens):
tokens = tokens.cpu().numpy().tolist()
if chat_format == "chatml":
return _decode_chatml(
tokens,
stop_words=[],
eod_token_ids=[tokenizer.im_start_id, tokenizer.im_end_id],
tokenizer=tokenizer,
raw_text_len=raw_text_len,
context_length=context_length,
verbose=verbose,
return_end_reason=return_end_reason,
errors=errors,
)
elif chat_format == "raw":
return _decode_default(
tokens,
stop_words=["<|endoftext|>"],
eod_words=["<|endoftext|>"],
tokenizer=tokenizer,
raw_text_len=raw_text_len,
verbose=verbose,
return_end_reason=return_end_reason,
errors=errors,
)
else:
raise NotImplementedError(f"Unknown chat format {chat_format!r}")
class StopWordsLogitsProcessor(LogitsProcessor):
"""
:class:`transformers.LogitsProcessor` that enforces that when specified sequences appear, stop geration.
Args:
stop_words_ids (:obj:`List[List[int]]`):
List of list of token ids of stop ids. In order to get the tokens of the words
that should not appear in the generated text, use :obj:`tokenizer(bad_word,
add_prefix_space=True).input_ids`.
eos_token_id (:obj:`int`):
The id of the `end-of-sequence` token.
"""
def __init__(self, stop_words_ids: Iterable[Iterable[int]], eos_token_id: int):
if not isinstance(stop_words_ids, List) or len(stop_words_ids) == 0:
raise ValueError(
f"`stop_words_ids` has to be a non-emtpy list, but is {stop_words_ids}."
)
if any(not isinstance(bad_word_ids, list) for bad_word_ids in stop_words_ids):
raise ValueError(
f"`stop_words_ids` has to be a list of lists, but is {stop_words_ids}."
)
if any(
any(
(not isinstance(token_id, (int, np.integer)) or token_id < 0)
for token_id in stop_word_ids
)
for stop_word_ids in stop_words_ids
):
raise ValueError(
f"Each list in `stop_words_ids` has to be a list of positive integers, but is {stop_words_ids}."
)
self.stop_words_ids = list(
filter(
lambda bad_token_seq: bad_token_seq != [eos_token_id], stop_words_ids
)
)
self.eos_token_id = eos_token_id
for stop_token_seq in self.stop_words_ids:
assert (
len(stop_token_seq) > 0
), "Stop words token sequences {} cannot have an empty list".format(
stop_words_ids
)
def __call__(
self, input_ids: torch.LongTensor, scores: torch.FloatTensor
) -> torch.FloatTensor:
stopped_samples = self._calc_stopped_samples(input_ids)
for i, should_stop in enumerate(stopped_samples):
if should_stop:
scores[i, self.eos_token_id] = float(2**15)
return scores
def _tokens_match(self, prev_tokens: torch.LongTensor, tokens: List[int]) -> bool:
if len(tokens) == 0:
# if bad word tokens is just one token always ban it
return True
elif len(tokens) > len(prev_tokens):
# if bad word tokens are longer then prev input_ids they can't be equal
return False
elif prev_tokens[-len(tokens) :].tolist() == tokens:
# if tokens match
return True
else:
return False
def _calc_stopped_samples(self, prev_input_ids: Iterable[int]) -> Iterable[int]:
stopped_samples = []
for prev_input_ids_slice in prev_input_ids:
match = False
for stop_token_seq in self.stop_words_ids:
if self._tokens_match(prev_input_ids_slice, stop_token_seq):
# if tokens do not match continue
match = True
break
stopped_samples.append(match)
return stopped_samples
def top_k_logits(logits, top_k=0, top_p=0.0, filter_value=-float("Inf")):
"""This function has been mostly taken from huggingface conversational
ai code at
https://medium.com/huggingface/how-to-build-a-state-of-the-art-
conversational-ai-with-transfer-learning-2d818ac26313"""
if top_k > 0:
# Remove all tokens with a probability less than the
# last token of the top-k
indices_to_remove = logits < torch.topk(logits, top_k)[0][..., -1, None]
logits[indices_to_remove] = filter_value
if top_p > 0.0:
# Cconvert to 1D
sorted_logits, sorted_indices = torch.sort(logits, descending=True, dim=-1)
cumulative_probs = torch.cumsum(F.softmax(sorted_logits, dim=-1), dim=-1)
# Remove tokens with cumulative probability above the threshold
sorted_indices_to_remove = cumulative_probs > top_p
# Shift the indices to the right to keep also the first token
# above the threshold
sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
sorted_indices_to_remove[..., 0] = 0
for i in range(sorted_indices.size(0)):
indices_to_remove = sorted_indices[i][sorted_indices_to_remove[i]]
logits[i][indices_to_remove] = filter_value
return logits
def switch(val1, val2, boolean):
boolean = boolean.type_as(val1)
return (1 - boolean) * val1 + boolean * val2

1
special_tokens_map.json Normal file
View File

@@ -0,0 +1 @@
{}

246
tokenization_qwen.py Normal file
View File

@@ -0,0 +1,246 @@
# Copyright (c) Alibaba Cloud.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
"""Tokenization classes for QWen."""
import base64
import logging
import os
import unicodedata
from typing import Collection, Dict, List, Set, Tuple, Union
import tiktoken
from transformers import PreTrainedTokenizer, AddedToken
logger = logging.getLogger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
ENDOFTEXT = "<|endoftext|>"
IMSTART = "<|im_start|>"
IMEND = "<|im_end|>"
# as the default behavior is changed to allow special tokens in
# regular texts, the surface forms of special tokens need to be
# as different as possible to minimize the impact
EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
SPECIAL_TOKENS = (
ENDOFTEXT,
IMSTART,
IMEND,
) + EXTRAS
def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
with open(tiktoken_bpe_file, "rb") as f:
contents = f.read()
return {
base64.b64decode(token): int(rank)
for token, rank in (line.split() for line in contents.splitlines() if line)
}
class QWenTokenizer(PreTrainedTokenizer):
"""QWen tokenizer."""
vocab_files_names = VOCAB_FILES_NAMES
def __init__(
self,
vocab_file,
errors="replace",
**kwargs,
):
super().__init__(**kwargs)
self.errors = errors # how to handle errors in decoding
self.mergeable_ranks = _load_tiktoken_bpe(vocab_file) # type: dict[bytes, int]
self.special_tokens = {
token: index
for index, token in enumerate(
SPECIAL_TOKENS, start=len(self.mergeable_ranks)
)
}
enc = tiktoken.Encoding(
"Qwen",
pat_str=PAT_STR,
mergeable_ranks=self.mergeable_ranks,
special_tokens=self.special_tokens,
)
assert (
len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
self.decoder = {
v: k for k, v in self.mergeable_ranks.items()
} # type: dict[int, bytes|str]
self.decoder.update({v: k for k, v in self.special_tokens.items()})
self.tokenizer = enc # type: tiktoken.Encoding
self.eod_id = self.tokenizer.eot_token
self.im_start_id = self.special_tokens[IMSTART]
self.im_end_id = self.special_tokens[IMEND]
def __getstate__(self):
# for pickle lovers
state = self.__dict__.copy()
del state['tokenizer']
return state
def __setstate__(self, state):
# tokenizer is not python native; don't pass it; rebuild it
self.__dict__.update(state)
enc = tiktoken.Encoding(
"Qwen",
pat_str=PAT_STR,
mergeable_ranks=self.mergeable_ranks,
special_tokens=self.special_tokens,
)
self.tokenizer = enc
def __len__(self) -> int:
return self.tokenizer.n_vocab
def get_vocab(self) -> Dict[bytes, int]:
return self.mergeable_ranks
def convert_tokens_to_ids(
self, tokens: Union[bytes, str, List[Union[bytes, str]]]
) -> List[int]:
ids = []
if isinstance(tokens, (str, bytes)):
if tokens in self.special_tokens:
return self.special_tokens[tokens]
else:
return self.mergeable_ranks.get(tokens)
for token in tokens:
if token in self.special_tokens:
ids.append(self.special_tokens[token])
else:
ids.append(self.mergeable_ranks.get(token))
return ids
def _add_tokens(self, new_tokens: Union[List[str], List[AddedToken]], special_tokens: bool = False) -> int:
if not special_tokens and new_tokens:
raise ValueError('Adding regular tokens is not supported')
for token in new_tokens:
surface_form = token.content if isinstance(token, AddedToken) else token
if surface_form not in SPECIAL_TOKENS:
raise ValueError('Adding unknown special tokens is not supported')
return 0
def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
"""
Save only the vocabulary of the tokenizer (vocabulary).
Returns:
`Tuple(str)`: Paths to the files saved.
"""
file_path = os.path.join(save_directory, "qwen.tiktoken")
with open(file_path, "w", encoding="utf8") as w:
for k, v in self.mergeable_ranks.items():
line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
w.write(line)
return (file_path,)
def tokenize(
self,
text: str,
allowed_special: Union[Set, str] = "all",
disallowed_special: Union[Collection, str] = (),
**kwargs,
) -> List[Union[bytes, str]]:
"""
Converts a string in a sequence of tokens.
Args:
text (`str`):
The sequence to be encoded.
allowed_special (`Literal["all"]` or `set`):
The surface forms of the tokens to be encoded as special tokens in regular texts.
Default to "all".
disallowed_special (`Literal["all"]` or `Collection`):
The surface forms of the tokens that should not be in regular texts and trigger errors.
Default to an empty tuple.
kwargs (additional keyword arguments, *optional*):
Will be passed to the underlying model specific encode method.
Returns:
`List[bytes|str]`: The list of tokens.
"""
tokens = []
text = unicodedata.normalize("NFC", text)
# this implementation takes a detour: text -> token id -> token surface forms
for t in self.tokenizer.encode(
text, allowed_special=allowed_special, disallowed_special=disallowed_special
):
tokens.append(self.decoder[t])
return tokens
def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
"""
Converts a sequence of tokens in a single string.
"""
text = ""
temp = b""
for t in tokens:
if isinstance(t, str):
if temp:
text += temp.decode("utf-8", errors=self.errors)
temp = b""
text += t
elif isinstance(t, bytes):
temp += t
else:
raise TypeError("token should only be of type types or str")
if temp:
text += temp.decode("utf-8", errors=self.errors)
return text
@property
def vocab_size(self):
return self.tokenizer.n_vocab
def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
"""Converts an id to a token, special tokens included"""
if index in self.decoder:
return self.decoder[index]
raise ValueError("unknown ids")
def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
"""Converts a token to an id using the vocab, special tokens included"""
if token in self.special_tokens:
return self.special_tokens[token]
if token in self.mergeable_ranks:
return self.mergeable_ranks[token]
raise ValueError("unknown token")
def _tokenize(self, text: str, **kwargs):
"""
Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
Do NOT take care of added tokens.
"""
raise NotImplementedError
def _decode(
self,
token_ids: Union[int, List[int]],
skip_special_tokens: bool = False,
errors: str = None,
**kwargs,
) -> str:
if isinstance(token_ids, int):
token_ids = [token_ids]
if skip_special_tokens:
token_ids = [i for i in token_ids if i < self.eod_id]
return self.tokenizer.decode(token_ids, errors=errors or self.errors)

11
tokenizer_config.json Normal file
View File

@@ -0,0 +1,11 @@
{
"auto_map": {
"AutoTokenizer": [
"tokenization_qwen.QWenTokenizer",
null
]
},
"clean_up_tokenization_spaces": true,
"model_max_length": 8192,
"tokenizer_class": "QWenTokenizer"
}