Commit
•
6ada6f7
1
Parent(s):
41bad26
End of training
Browse files
README.md
CHANGED
|
@@ -2,12 +2,13 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
-
- generated_from_trainer
|
| 8 |
base_model: mistralai/Mistral-7B-v0.1
|
| 9 |
datasets:
|
| 10 |
-
-
|
| 11 |
model-index:
|
| 12 |
- name: zephyr-7b-sft-qlora-alignment-10000
|
| 13 |
results: []
|
|
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# zephyr-7b-sft-qlora-alignment-10000
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 1.2123
|
| 24 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- sft
|
|
|
|
| 9 |
base_model: mistralai/Mistral-7B-v0.1
|
| 10 |
datasets:
|
| 11 |
+
- robust-control/PKU-alignment-better-safer-2
|
| 12 |
model-index:
|
| 13 |
- name: zephyr-7b-sft-qlora-alignment-10000
|
| 14 |
results: []
|
|
|
|
| 19 |
|
| 20 |
# zephyr-7b-sft-qlora-alignment-10000
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the robust-control/PKU-alignment-better-safer-2 dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
- Loss: 1.2123
|
| 25 |
|