revise description
Browse files
README.md
CHANGED
@@ -4,11 +4,11 @@
|
|
4 |
{}
|
5 |
---
|
6 |
|
7 |
-
#
|
8 |
|
9 |
<!-- Provide a quick summary of what the model is/does. -->
|
10 |
|
11 |
-
Model developed by Collective AI for role-playing.
|
12 |
|
13 |
### Model Description
|
14 |
|
@@ -17,7 +17,7 @@ Model developed by Collective AI for role-playing.
|
|
17 |
|
18 |
|
19 |
- **Developed by:** [Collective AI](https://huggingface.co/collective-ai)
|
20 |
-
- **Model type:** llama3 based model
|
21 |
- **Language(s):** Chinese, English
|
22 |
- **Finetuned from model:** [Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat)
|
23 |
|
@@ -117,32 +117,18 @@ Coming soon
|
|
117 |
|
118 |
|
119 |
## Improvement
|
120 |
-
|
121 |
-
|
122 |
-
一、富表征表达能力
|
123 |
-
该模型能够通过对话内容中的细节描写,如言语表达、非语言线索和人物心理表现等多维表达手法,弥补文本信息的不足,帮助更充分传达语义与情感内涵。
|
124 |
-
二、出色的对话引导能力
|
125 |
-
该模型不仅能根据用户多样的输入内容进行灵活应对,在用户表达欠缺时也能主动提出新话题继续交流,极大扩展了对话的潜在长度和深度。它较难陷入简单重复。
|
126 |
-
三、强大的语料支持基础
|
127 |
-
该模型通过海量优质中文语料的训练,能够根据不同场景设定及人物属性展开多样主题的对话,包括古风、校园、职场乃至奇幻等题材,提供用户更丰富多彩的语言交互体验。
|
128 |
-
|
129 |
-
所以在对话方面,我们的模型相较于ChatGPT提升约150%。其对话轮次能从传统水平的80轮提升至200轮甚至更多,显著扩充用户的沟通体验。
|
130 |
-
|
131 |
-
英文版本 :
|
132 |
-
In terms of dialog sustenance, our model demonstrates around 150% improvement over ChatGPT in terms of the number of utterances per conversation. It can extend the average dialog turns from the conventional 80 replies to as many as 200 turns or more, significantly enhancing the user communication experience.
|
133 |
-
|
134 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65fc22b1ec1f99ad1f3501f4/ttA_3Qtlu1WKFloZ5-y6j.png)
|
135 |
|
136 |
|
137 |
-
Here is the translation into professional English:
|
138 |
Our chatbot model has several distinctive strengths:
|
139 |
-
|
140 |
-
The model
|
141 |
-
|
142 |
-
The model can not only flexibly engage with users’ diverse inputs, but also proactively introduce new topics to continue the exchange when user expression is lacking - greatly expanding the potential length and depth of conversations. It is less susceptible to simplistic repetitions.
|
143 |
-
3. Strong Linguistic Foundations
|
144 |
-
By leveraging massive high-quality Chinese corpora, the model can host conversations on diverse topics such as historical, campus, workplace and even fantasy themes according to different scenario settings and character attributes, providing users with richer linguistic interaction experiences.
|
145 |
|
|
|
|
|
146 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65fc22b1ec1f99ad1f3501f4/mO36170XQrUz5lfJU1b81.png)
|
147 |
|
148 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65fc22b1ec1f99ad1f3501f4/DeJM3tos5lorHnEZiKNyp.png)
|
|
|
4 |
{}
|
5 |
---
|
6 |
|
7 |
+
# Collective roleplay model
|
8 |
|
9 |
<!-- Provide a quick summary of what the model is/does. -->
|
10 |
|
11 |
+
Model developed by Collective AI for role-playing with learning from user interactions data.
|
12 |
|
13 |
### Model Description
|
14 |
|
|
|
17 |
|
18 |
|
19 |
- **Developed by:** [Collective AI](https://huggingface.co/collective-ai)
|
20 |
+
- **Model type:** llama3 based role-play model
|
21 |
- **Language(s):** Chinese, English
|
22 |
- **Finetuned from model:** [Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat)
|
23 |
|
|
|
117 |
|
118 |
|
119 |
## Improvement
|
120 |
+
Our model demonstrates around 150% improvement over ChatGPT in terms of average conversation length. It can extend the average dialog turns from 80 replies to as many as 200 turns or more, significantly improving user engagement.
|
121 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65fc22b1ec1f99ad1f3501f4/ttA_3Qtlu1WKFloZ5-y6j.png)
|
123 |
|
124 |
|
|
|
125 |
Our chatbot model has several distinctive strengths:
|
126 |
+
**Rich Expressiveness**: The model is capable of conveying semantic and emotional nuances by utilizing detailed descriptions within the dialogue, such as speech expression, non-verbal cues, and character psychological portrayals, complementing the insufficiency of pure textual information.
|
127 |
+
**Proactivity**: The model can not only flexibly engage with users’ diverse inputs, but also proactively introduce new topics, which greatly improved user retention and depth of conversations. It's also less susceptible to repetitions.
|
128 |
+
**Strong Linguistic Foundations**: By leveraging massive high-quality Chinese corpora, the model can engage in diverse conversations based on different scenarios and character attributes, including genres like historical, campus, workplace, and fantasy, providing users with richer chat experiences.
|
|
|
|
|
|
|
129 |
|
130 |
+
Here are some example roleplay dialogues from our model:
|
131 |
+
|
132 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65fc22b1ec1f99ad1f3501f4/mO36170XQrUz5lfJU1b81.png)
|
133 |
|
134 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65fc22b1ec1f99ad1f3501f4/DeJM3tos5lorHnEZiKNyp.png)
|