Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
jasperyeoh2
/
mistral-dpo-peft
like
0
PEFT
Safetensors
mistral
dpo
preference-optimization
lora
instruction-tuning
alpaca-eval
License:
mit
Model card
Files
Files and versions
Community
Use this model
jasperyeoh2
commited on
Apr 25
Commit
cae8908
·
verified
·
1 Parent(s):
d6e35e1
Create README.md
Browse files
Files changed (1)
hide
show
README.md
+10
-0
README.md
ADDED
Viewed
@@ -0,0 +1,10 @@
1
+
---
2
+
datasets:
3
+
- jasperyeoh2/pairrm-preference-dataset
4
+
- GAIR/lima
5
+
base_model:
6
+
- mistralai/Mistral-7B-Instruct-v0.2
7
+
tags:
8
+
- PEFT
9
+
- DPO
10
+
---