Update README from local repo
Browse files
README.md
CHANGED
|
@@ -136,8 +136,6 @@ We did not train the model to recognize non-response in any language other than
|
|
| 136 |
|
| 137 |
As the model was fine-tuned from SimCSE, itself fine-tuned from BERT, it will reproduce all biases inherent in these base models. Due to tokenization, the model may incorrectly classify typos, especially in acronyms. For example: `LGBTQ` is valid, while `LBGTQ` is classified as gibberish.
|
| 138 |
|
| 139 |
-
Some examples of refusal responses also can appear to be valid as they did not occur in our limited training set. For example, `none of your business` is currently returned as valid as it was not a response seen in the first two rounds of RANDS during COVID 19.
|
| 140 |
-
|
| 141 |
## Training
|
| 142 |
|
| 143 |
#### Training Data
|
|
|
|
| 136 |
|
| 137 |
As the model was fine-tuned from SimCSE, itself fine-tuned from BERT, it will reproduce all biases inherent in these base models. Due to tokenization, the model may incorrectly classify typos, especially in acronyms. For example: `LGBTQ` is valid, while `LBGTQ` is classified as gibberish.
|
| 138 |
|
|
|
|
|
|
|
| 139 |
## Training
|
| 140 |
|
| 141 |
#### Training Data
|