Skip to content

Commit

Permalink
Merge pull request THUDM#62 from GanymedeNil/main
Browse files Browse the repository at this point in the history
Add some parameter support in web demo
  • Loading branch information
duzx16 authored Mar 17, 2023
2 parents fc4ac83 + 702c2ca commit ecd2857
Show file tree
Hide file tree
Showing 11 changed files with 135 additions and 8 deletions.
63 changes: 63 additions & 0 deletions .github/ISSUE_TEMPLATE/bug_report.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,63 @@
name: 🐞 Bug/Help
description: File a bug/issue
title: "[BUG/Help] <title>"
labels: []
body:
- type: checkboxes
attributes:
label: Is there an existing issue for this?
description: Please search to see if an issue already exists for the bug you encountered.
options:
- label: I have searched the existing issues
required: true
- type: textarea
attributes:
label: Current Behavior
description: |
A concise description of what you're experiencing, with screenshot attached if possible.
Tip: You can attach images or log files by clicking this area to highlight it and then dragging files in.
validations:
required: true
- type: textarea
attributes:
label: Expected Behavior
description: A concise description of what you expected to happen.
validations:
required: false
- type: textarea
attributes:
label: Steps To Reproduce
description: Steps to reproduce the behavior.
placeholder: |
1. In this environment...
2. With this config...
3. Run '...'
4. See error...
validations:
required: true
- type: textarea
attributes:
label: Environment
description: |
examples:
- **OS**: Ubuntu 20.04
- **Python**: 3.8
- **Transformers**: 4.26.1
- **PyTorch**: 1.12
- **CUDA Support**: True
value: |
- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :
render: markdown
validations:
required: true
- type: textarea
attributes:
label: Anything else?
description: |
Links? References? Anything that will give us more context about the issue you are encountering!
validations:
required: false
1 change: 1 addition & 0 deletions .github/ISSUE_TEMPLATE/config.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
blank_issues_enabled: false
26 changes: 26 additions & 0 deletions .github/ISSUE_TEMPLATE/feature_request.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
name: Feature request
description: Suggest an idea for this project
title: "[Feature] <title>"
labels: []
body:
- type: textarea
attributes:
label: Is your feature request related to a problem? Please describe.
description: |
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
validations:
required: false
- type: textarea
attributes:
label: Solutions
description: |
Describe the solution you'd like
A clear and concise description of what you want to happen.
validations:
required: true
- type: textarea
attributes:
label: Additional context
description: Add any other context or screenshots about the feature request here.
validations:
required: false
37 changes: 34 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,10 @@

## 介绍

ChatGLM-6B 是一个开源的、支持中英双语的对话语言模型,基于 [General Language Model (GLM)](https://github.com/THUDM/GLM) 架构,具有 62 亿参数。结合模型量化技术,用户可以在消费级的显卡上进行本地部署(INT4 量化级别下最低只需 6GB 显存)。ChatGLM-6B 使用了和 ChatGPT 相似的技术,针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练,辅以监督微调、反馈自助、人类反馈强化学习等技术的加持,62 亿参数的 ChatGLM-6B 已经能生成相当符合人类偏好的回答。更多信息请参考我们的[博客](https://chatglm.cn/blog)
ChatGLM-6B 是一个开源的、支持中英双语的对话语言模型,基于 [General Language Model (GLM)](https://github.com/THUDM/GLM) 架构,具有 62 亿参数。结合模型量化技术,用户可以在消费级的显卡上进行本地部署(INT4 量化级别下最低只需 6GB 显存)。
ChatGLM-6B 使用了和 ChatGPT 相似的技术,针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练,辅以监督微调、反馈自助、人类反馈强化学习等技术的加持,62 亿参数的 ChatGLM-6B 已经能生成相当符合人类偏好的回答。更多信息请参考我们的[博客](https://chatglm.cn/blog)

同时,我们基于千亿基座的[ChatGLM 模型](https://chatglm.cn)正在邀请制内测,后续将逐步扩大内测范围,欢迎申请加入内测
不过,由于ChatGLM-6B的规模较小,目前已知其具有相当多的[**局限性**](#局限性),如事实性/数学逻辑错误,可能生成有害/有偏见内容,较弱的上下文能力,自我认知混乱,以及对英文指示生成与中文指示完全矛盾的内容。请大家在使用前了解这些问题,以免产生误解

*Read this in [English](README_en.md).*

Expand Down Expand Up @@ -46,7 +47,7 @@ ChatGLM-6B 是一个开源的、支持中英双语的对话语言模型,基于

如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。
```
完整的模型实现可以在 [Hugging Face Hub](https://huggingface.co/THUDM/chatglm-6b) 上查看。
完整的模型实现可以在 [Hugging Face Hub](https://huggingface.co/THUDM/chatglm-6b) 上查看。如果你从Hugging Face Hub上下载checkpoint的速度较慢,也可以从[这里](https://cloud.tsinghua.edu.cn/d/fb9f16d6dc8f482596c2/)手动下载。

### Demo

Expand Down Expand Up @@ -107,6 +108,8 @@ model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).bf
```
需保证空闲内存接近16G,并且推理速度会很慢。

MacOS 如果报错`RuntimeError: Unknown platform: darwin`的话请参考这个[Issue](https://github.com/THUDM/ChatGLM-6B/issues/6#issuecomment-1470060041).

## ChatGLM-6B示例

以下是一些使用`web_demo.py`得到的示例截图。更多ChatGLM-6B的可能,等待你来探索发现!
Expand Down Expand Up @@ -163,6 +166,34 @@ model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).bf

</details>

## 局限性

由于ChatGLM-6B的小规模,其能力仍然有许多局限性。以下是我们目前发现的一些问题:

- 模型容量较小:6B的小容量,决定了其相对较弱的模型记忆和语言能力。在面对许多事实性知识任务时,ChatGLM-6B可能会生成不正确的信息;它也不擅长逻辑类问题(如数学、编程)的解答。
<details><summary><b>点击查看例子</b></summary>

![](limitations/factual_error.png)

![](limitations/math_error.png)

</details>

- 产生有害说明或有偏见的内容:ChatGLM-6B只是一个初步与人类意图对齐的语言模型,可能会生成有害、有偏见的内容。(内容可能具有冒犯性,此处不展示)

- 英文能力不足:ChatGLM-6B 训练时使用的指示/回答大部分都是中文的,仅有极小一部分英文内容。因此,如果输入英文指示,回复的质量远不如中文,甚至与中文指示下的内容矛盾,并且出现中英夹杂的情况。

- 易被误导,对话能力较弱:ChatGLM-6B 对话能力还比较弱,而且 “自我认知” 存在问题,并很容易被误导并产生错误的言论。例如当前版本的模型在被误导的情况下,会在自我认知上发生偏差。
<details><summary><b>点击查看例子</b></summary>

![](limitations/self-confusion_google.jpg)

![](limitations/self-confusion_openai.jpg)

![](limitations/self-confusion_tencent.jpg)

</details>

## 协议

本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源,ChatGLM-6B 模型的权重的使用则需要遵循 [Model License](MODEL_LICENSE)
Expand Down
Binary file added limitations/factual_error.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added limitations/math_error.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added limitations/self-confusion_google.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added limitations/self-confusion_openai.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added limitations/self-confusion_tencent.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
1 change: 1 addition & 0 deletions requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -2,3 +2,4 @@ protobuf>=3.19.5,<3.20.1
transformers>=4.26.1
icetk
cpm_kernels
torch>=1.10
15 changes: 10 additions & 5 deletions web_demo.py
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,11 @@
MAX_BOXES = MAX_TURNS * 2


def predict(input, history=None):
def predict(input, max_length, top_p, temperature, history=None):
if history is None:
history = []
response, history = model.chat(tokenizer, input, history)
response, history = model.chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
temperature=temperature)
updates = []
for query, response in history:
updates.append(gr.update(visible=True, value="用户:" + query))
Expand All @@ -33,8 +34,12 @@ def predict(input, history=None):

with gr.Row():
with gr.Column(scale=4):
txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter").style(container=False)
txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter", lines=11).style(
container=False)
with gr.Column(scale=1):
max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
button = gr.Button("Generate")
button.click(predict, [txt, state], [state] + text_boxes)
demo.queue().launch(share=True)
button.click(predict, [txt, max_length, top_p, temperature, state], [state] + text_boxes)
demo.queue().launch(share=True, inbrowser=True)

0 comments on commit ecd2857

Please sign in to comment.