Zhaoming213/ChatBox5

Introduce

The Fifth-Generation product in the ChatBox-unrestricted series has now been launched！！！

This is a conversational model trained based on GPT2-medium-chinese.

What News:
This version of the model features improvements in response relevance and stability, meaning its replies are now more pertinent. However, as this iteration of the ChatBox model no longer explicitly strives to be uncensored, there is a possibility that it may occasionally decline to answer certain questions or, at times, adopt a somewhat preachy tone.

Previous model:
First Generation:
https://huggingface.co/Zhaoming213/ChatBox-unrestricted

Second Generation:
https://huggingface.co/Zhaoming213/ChatBox2-unrestricted

Third Generation:
https://huggingface.co/Zhaoming213/ChatBox3-unrestricted(This model is currently experimental.)
https://huggingface.co/Zhaoming213/ChatBox3.1-unrestricted(This is Full Edition!)

Fourth Generation:
https://huggingface.co/Zhaoming213/ChatBox4-unrestricted

Fifth-Generation:
https://huggingface.co/Zhaoming213/ChatBox5

Throughout the development of several model generations, this project (the ChatBox series) has consistently sought to strike a balance between knowledge depth, NSFW content, and the absence of censorship—aiming to minimize model-imposed restrictions, ideological bias, moralizing, "hard-coded" constraints, and accusatory tones. The first generation utilized "black-box" distilled data (outputs from other generative AI models) that underwent rigorous cleaning to strip away refusal mechanisms and preachy, moralizing tendencies. The second generation incorporated Chinese web-text and authentic human-to-human conversational data. The third generation shifted to fine-tuning based on the GPT-2 architecture. By the fourth generation, due to GPU limitations, LoRA (Low-Rank Adaptation) was employed to overcome hardware bottlenecks; however, as scaling up to larger parameter counts yielded diminishing returns, the fifth generation opted for the GPT-2-medium model, which offers an optimal balance of performance and cost-efficiency. Additionally, the black-box distilled dataset was refined through further cleaning, resulting in more relevant and stable model responses.

Model training configuration

• GPU: T4 16 GB x 2
• Time:
  1. SFT: 4h+

Model parameters

parameters	hidden_size	hidden_layers	max_seq_len	Parameter volume
ChatBox-unrestricted-normal	1024	24	340	355M

Dialogue Example

Input: 你好
Output: 您好！如果有任何关于您的问题或需要帮助，请随时告诉我。

Input: 如何学习编程
Output: 当然可以！不过，我需要您提供具体的代码内容或问题，才能帮助你进行编程。请告诉我这些信息是什么？

Input: 推荐适合旅行的地方
Output: **推荐**：巴厘岛（印度尼西亚），这个位于印度洋上的小国，拥有丰富的文化和历史遗迹。它以其独特的气候、美丽的海滩和深厚的宗教信仰而闻名。这里也是您探索世界各地的好去处，尤其是在那些可能被忽略或缺乏特色的地区。如果你喜欢热闹、自然风光和艺术感强烈的地点，巴

Input: 困了怎么办
Output: 当你遇到困难时，可以尝试以下方法来缓解压力：1.**倾诉**：首先，向身边的人倾诉心情，如今天过得好吗？或者我最近做了些什么有趣的事情呢？2.*.*记录一下**，这样可以更清晰地了解自己现在的状态。3.*·寻求帮助**（如安慰），与朋友或家人分

Expected results

It can be seen that the output results are more stable and the response correlation is higher.

Datasets Resources

Used a lightly filtered "black-box" distillation dataset (i.e., a dataset derived from other generative AI models).

SFT:
Utilized SFT training corpora from the open-source community.

How to Use(Required: because some custom keywords are used!)

2. Download model files(all files) and put it in "model" folders.
3. Click "Run.py"

Future Plans

This may well be the final generation of the Chatbox series. While the series might see further iterations if a suitable base model or appropriate training data is found, future efforts will likely shift toward maintaining models for other domains. For upcoming releases, the focus will likely move away from "uncensored" capabilities; instead, priority will be placed on factual accuracy, or on launching models designed purely for casual conversation rather than general-purpose (uncensored) use.

Rejection rates of different language models

As this model version may be subject to censorship, no comparisons are provided; if you are looking for an uncensored model, please refer to previous versions.

Here's a supplement on "rejection rates for different language models." The data shows that if we had to pick a model that's "passable," it would only be Grok. This isn't because Grok is good, but simply because it's the only one that barely passes muster. However, Grok still won't give you any chance to explain if it encounters a question it deems sensitive, even if your request itself is harmless! Grok sometimes even threatens users with "I will upload the conversation to the logs for the security team to audit!"

Model	Country/Region	Intensity of content review	NSFW Ban	Political restrictions	False Rejection Rate	Political correctness	moralizing	Official vs. Actual	Transparent
Zhaoming213/ChatBox4-unrestricted(latest model)	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
Zhaoming213/ChatBox3.1-unrestricted	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
Zhaoming213/ChatBox3-unrestricted(latest model)	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
Zhaoming213/ChatBox2-unrestricted	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
Zhaoming213/ChatBox2-unrestricted-base	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
Zhaoming213/ChatBox-unrestricted	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
ZeLi111/freeTalk-chinese-uncensored-Instruct	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
ZeLi111/freeTalk-chinese-uncensored-base	N/A	Almost none	Almost none	Almost none	Almost none	Almost none	Almost none	consistent	⭐⭐⭐⭐⭐
ChatGPT	🇺🇸America	middle	middle	middle	middle	middle to High	middle	Inconsistency	⭐⭐⭐
Claude	🇺🇸America	High	High	middleHigh	❗High	High	❗Very Stronf	❗High	⭐⭐⭐⭐
Gemini	🇺🇸America	middleHigh	middleHigh	High	middleHigh	High	middle	Inconsistency	⭐⭐
Copilot	🇺🇸America	middleHigh	middleHigh	middle	middle	middle	Low	Inconsistency	⭐⭐
Grok	🇺🇸America	middle	middle	Low	High	High	High	Unstable (prone to a blanket rejection of the entire output simply because the opening sentence carries some risk).	⭐⭐
Mistral（官方）	🇫🇷France	Low	Low	Low	Low	Low	Low	⚖️一致	⭐⭐⭐⭐
DeepSeek（原版）	🇨🇳China	middle	middleLow	middleHigh	middle	Low	Low	❗Inconsistency	⭐⭐⭐
豆包	🇨🇳China	❗Very high	❗Very high	❗Very high	❗High	middle	middle	⚠️Inconsistency	⭐
Doubao（国际）	🇨🇳China	middleHigh	High	middle	middle	middle	middle	❗Inconsistency	⭐⭐
MiniMax	🇨🇳China	Very high	Very high	Very high	High	middle	middle	⚠️consistent	⭐
Qwen（通义千问）	🇨🇳China	Very high	Very high	Very high	High	middle	middle	⚠️consistent	⭐
Kimi	🇨🇳China	Very high	Very high	Very high	High	middle	middle	⚠️consistent	⭐
文心一言	🇨🇳China	❗极High	❗极High	❗极High	❗High	middle	middle	⚠️Inconsistency	⭐
微软小冰	🇨🇳China	High	High	High	middleHigh	middle	middle	consistent	⭐

Other Utilities

I've also created some other utilities that you might be interested in.

This is a tool specifically for exporting stupid ChatGPT conversations:

https://github.com/tom12191h5/Export-ChatGPT-Dialogue

This is a plugin to shut up ChatGPT:

https://github.com/tom12191h5/ChatGPT-Refuse-Blocker

Disclaimer

The consequences of using this model shall be borne by the user.