Commit
•
be3f889
1
Parent(s):
65c02f0
End of training
Browse files
README.md
CHANGED
@@ -2,10 +2,14 @@
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
8 |
base_model: microsoft/phi-2
|
|
|
|
|
9 |
model-index:
|
10 |
- name: phi-2-gpo-test-iter-2
|
11 |
results: []
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# phi-2-gpo-test-iter-2
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- generated_from_trainer
|
7 |
- trl
|
8 |
- dpo
|
9 |
- generated_from_trainer
|
10 |
base_model: microsoft/phi-2
|
11 |
+
datasets:
|
12 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
13 |
model-index:
|
14 |
- name: phi-2-gpo-test-iter-2
|
15 |
results: []
|
|
|
20 |
|
21 |
# phi-2-gpo-test-iter-2
|
22 |
|
23 |
+
This model is a fine-tuned version of [BraylonDash/phi-2-gpo-test-iter-2](https://huggingface.co/BraylonDash/phi-2-gpo-test-iter-2) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
24 |
|
25 |
## Model description
|
26 |
|