Update README.md
Browse files
README.md
CHANGED
@@ -15,9 +15,10 @@ model-index:
|
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
-
#
|
|
|
|
|
19 |
|
20 |
-
This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-cai](https://huggingface.co/HuggingFaceH4/mistral-7b-cai) on the HuggingFaceH4/ultrafeedback_binarized_fixed and the HuggingFaceH4/cai-conversation-harmless datasets.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: 0.6327
|
23 |
- Rewards/chosen: -9.8716
|
|
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
# Mistral 7B Constitutional AI
|
19 |
+
|
20 |
+
This model is a DPO-aligned version of [HuggingFaceH4/mistral-7b-cai](https://huggingface.co/HuggingFaceH4/mistral-7b-cai) on the HuggingFaceH4/ultrafeedback_binarized_fixed and the HuggingFaceH4/cai-conversation-harmless datasets.
|
21 |
|
|
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.6327
|
24 |
- Rewards/chosen: -9.8716
|