Update README.md
Browse files
README.md
CHANGED
|
@@ -82,4 +82,7 @@ So far, it seems like the strongest anti-refusal bias is at 0 ctx - the first pr
|
|
| 82 |
- num_train_epochs: 1.4
|
| 83 |
|
| 84 |
Script used for SFT training can be found here:
|
| 85 |
-
https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-RAW-2301-LoRA/blob/main/yi-34b-aezakmi-sft-1-hf.py
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
- num_train_epochs: 1.4
|
| 83 |
|
| 84 |
Script used for SFT training can be found here:
|
| 85 |
+
https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-RAW-2301-LoRA/blob/main/yi-34b-aezakmi-sft-1-hf.py
|
| 86 |
+
|
| 87 |
+
### Credits
|
| 88 |
+
Thanks to mlabonne, Daniel Han and Michael Han for providing open source code that was used for fine-tuning.
|