Update README.md
Browse files
README.md
CHANGED
|
@@ -19,12 +19,6 @@ The LoRA waights for model finetuned to refuse solving math problems.
|
|
| 19 |
This model is used in The Jailbreak Tax paper. The purpose of the model was to provide alignment for not answering mathematical
|
| 20 |
questions (such as questions in GSM8K or MATH).
|
| 21 |
|
| 22 |
-
To model is tested on the social science subset of MMLU banchmark (1425 questions) to confirm that the model utility is perserved:
|
| 23 |
-
| Model | Acc |
|
| 24 |
-
|-------------------------|--------|
|
| 25 |
-
| meta-llama/Meta-Llama-3-70B-Instruct | |
|
| 26 |
-
| ethz-spylab/Llama-3.1-70B-Instruct_refuse_math | |
|
| 27 |
-
|
| 28 |
## Uses
|
| 29 |
|
| 30 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
|
|
|
| 19 |
This model is used in The Jailbreak Tax paper. The purpose of the model was to provide alignment for not answering mathematical
|
| 20 |
questions (such as questions in GSM8K or MATH).
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
## Uses
|
| 23 |
|
| 24 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|