PyTorch
mistral
Krutrim
language-model
krutrim-admin commited on
Commit
53e6f2d
·
verified ·
1 Parent(s): 1855160

Update README.md

Browse files

updated limitations

Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -159,11 +159,11 @@ Note: The provided chat template, which is the default chat template, helps gene
159
  We recommend using `temperature=0.3` for the best performance
160
 
161
  ## Limitations
162
- The model was trained on a dataset that includes content from the internet, which may contain toxic language, biases, and unsafe content. As a result, the model may:
163
- - Amplify biases present in the training data
164
- - Generate toxic responses, especially when prompted with toxic inputs
165
- - Provide inaccurate, incomplete, or redundant answers
166
- - Generate responses in languages inconsistent with the prompt
167
 
168
  ## License
169
  TBD
 
159
  We recommend using `temperature=0.3` for the best performance
160
 
161
  ## Limitations
162
+ The model was trained on a dataset that includes content from the internet, which may contain toxic language, biases, and unsafe content. The model has undergone extensive post-training to handle these and is continuously evolving. In response to some prompts the model might:
163
+ - amplify biases present in the training data
164
+ - generate toxic responses
165
+ - provide inaccurate, incomplete, or redundant answers
166
+ - generate responses in languages inconsistent with the prompt
167
 
168
  ## License
169
  TBD