Commit
•
7eb7356
1
Parent(s):
9dda971
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,10 +24,6 @@ This llama model was trained 2x faster with [Unsloth](https://github.com/unsloth
|
|
| 24 |
Overview
|
| 25 |
This model is meant to enhance adherence to provided context (e.g., for RAG applications) and reduce hallucinations, inspired by airoboros context-obedient question answer format.
|
| 26 |
|
| 27 |
-
---
|
| 28 |
-
license: cc-by-4.0
|
| 29 |
-
---
|
| 30 |
-
|
| 31 |
# Contextual DPO
|
| 32 |
|
| 33 |
## Overview
|
|
|
|
| 24 |
Overview
|
| 25 |
This model is meant to enhance adherence to provided context (e.g., for RAG applications) and reduce hallucinations, inspired by airoboros context-obedient question answer format.
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
# Contextual DPO
|
| 28 |
|
| 29 |
## Overview
|