Titovs jdev8 commited on
Commit
7015161
1 Parent(s): ed06d90

Update README.md (#2)

Browse files

- Update README.md (a616753db3aaa30552b323b7c7117b8189d0e2a4)


Co-authored-by: Anton Shapkin <[email protected]>

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -89,4 +89,4 @@ Fine-tuned model:
89
 
90
  # Ethical Considerations and Limitations
91
 
92
- Deepseek and its variants are a new technology that carries risks with use. The testing conducted to date could not cover all scenarios. For these reasons, as with all LLMs, Kexer's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of Kexer, developers should perform safety testing and tuning tailored to their specific applications of the model.
 
89
 
90
  # Ethical Considerations and Limitations
91
 
92
+ Deepseek-7B-Kexer and its variants are a new technology that carries risks with use. The testing conducted to date could not cover all scenarios. For these reasons, as with all LLMs, Deepseek-7B-Kexer potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of Deepseek-7B-Kexer, developers should perform safety testing and tuning tailored to their specific applications of the model.