shenzhi-wang commited on
Commit
9a38e0b
1 Parent(s): 4883c14

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -4
README.md CHANGED
@@ -11,11 +11,14 @@ tags:
11
  - orpo
12
  ---
13
 
14
- ❗️❗️❗️NOTICE: For optimal performance, we refrain from fine-tuning the model's identity. Thus, inquiries such as "Who are you" or "Who developed you" may yield random responses that are not necessarily accurate.
 
 
 
 
15
 
16
- 🌟 If you enjoy our model, please give it a star on our Hugging Face repo and kindly [cite our model](https://huggingface.co/shenzhi-wang/Gemma-2-27B-Chinese-Chat#citation). Your support means a lot to us. Thank you!
17
 
18
- ❗️❗️❗️ NOTICE: During fine-tuning, we opt for flash-attn-2 instead of the default eager attention used in Gemma2. For more details on this decision, please refer to [this discussion](https://huggingface.co/shenzhi-wang/Gemma-2-27B-Chinese-Chat/discussions/1).
19
 
20
  🌟 We have released [Gemma-2-9B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat). If you love our Gemma-2-27B-Chinese-Chat, don't miss out on our [Gemma-2-9B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat)!
21
 
@@ -30,7 +33,7 @@ tags:
30
 
31
  Gemma-2-27B-Chinese-Chat is **the first instruction-tuned language model built upon [google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) for Chinese & English users** with various abilities such as roleplaying & tool-using.
32
 
33
- Developed by: [Shenzhi Wang](https://shenzhi-wang.netlify.app)\*, [Yaowei Zheng](https://github.com/hiyouga)\*, Guoyin Wang (in.ai), Shiji Song, Gao Huang. (\*: Equal Contribution )
34
 
35
  - License: [Gemma License](https://ai.google.dev/gemma/terms)
36
  - Base Model: [google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)
 
11
  - orpo
12
  ---
13
 
14
+ > [!CAUTION]
15
+ > For optimal performance, we refrain from fine-tuning the model's identity. Thus, inquiries such as "Who are you" or "Who developed you" may yield random responses that are not necessarily accurate.
16
+
17
+ > [!CAUTION]
18
+ > During fine-tuning, we opt for flash-attn-2 instead of the default eager attention used in Gemma2. For more details on this decision, please refer to [this discussion](https://huggingface.co/shenzhi-wang/Gemma-2-27B-Chinese-Chat/discussions/1).
19
 
 
20
 
21
+ 🌟 If you enjoy our model, please give it a star on our Hugging Face repo and kindly [cite our model](https://huggingface.co/shenzhi-wang/Gemma-2-27B-Chinese-Chat#citation). Your support means a lot to us. Thank you!
22
 
23
  🌟 We have released [Gemma-2-9B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat). If you love our Gemma-2-27B-Chinese-Chat, don't miss out on our [Gemma-2-9B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Gemma-2-9B-Chinese-Chat)!
24
 
 
33
 
34
  Gemma-2-27B-Chinese-Chat is **the first instruction-tuned language model built upon [google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) for Chinese & English users** with various abilities such as roleplaying & tool-using.
35
 
36
+ Developers: [Shenzhi Wang](https://shenzhi-wang.netlify.app)\*, [Yaowei Zheng](https://github.com/hiyouga)\*, Guoyin Wang (in.ai), Shiji Song, Gao Huang. (\*: Equal Contribution )
37
 
38
  - License: [Gemma License](https://ai.google.dev/gemma/terms)
39
  - Base Model: [google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)