Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,9 @@ This model is the RLHF version of `HuggingFaceH4/mistral-7b-sft-beta` without an
|
|
| 4 |
The external signal includes (1) Reward model; (2) AI-generated Prompts.
|
| 5 |
|
| 6 |
|
| 7 |
-
**We obtain 35.95% win-rate on Alpaca Eval v2.** The win-rate of the base model is only 4.63%.
|
|
|
|
|
|
|
| 8 |
|
| 9 |
## Model Details
|
| 10 |
|
|
|
|
| 4 |
The external signal includes (1) Reward model; (2) AI-generated Prompts.
|
| 5 |
|
| 6 |
|
| 7 |
+
**We obtain 35.95% win-rate on Alpaca Eval v2.** The win-rate of the base model is only 4.63%.
|
| 8 |
+
|
| 9 |
+
We have shown the strong potential of iterative RLHF algorithm for LLMs to provide proper and well-behaved responses.
|
| 10 |
|
| 11 |
## Model Details
|
| 12 |
|