Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,4 @@ base_model:
|
|
| 6 |
- alignment-handbook/zephyr-7b-sft-full
|
| 7 |
---
|
| 8 |
|
| 9 |
-
DPO model for Mistral-Base under trl/ultradeedback_binarized finetuning.
|
|
|
|
| 6 |
- alignment-handbook/zephyr-7b-sft-full
|
| 7 |
---
|
| 8 |
|
| 9 |
+
DPO model excluding the noisy preference pairs for Mistral-Base under trl/ultradeedback_binarized finetuning.
|