Update README.md
Browse files
README.md
CHANGED
|
@@ -7,5 +7,14 @@ language:
|
|
| 7 |
---
|
| 8 |
|
| 9 |
*TODO:Upload pending, training is finished. still testing.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
-
Reproduce Vicuna, but based on yi-6B.
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
*TODO:Upload pending, training is finished. still testing.
|
| 10 |
+
*Update: Having a bit issue, still figuring things out.
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
Reproduce Vicuna, but based on yi-6B.
|
| 14 |
+
|
| 15 |
+
We can see from some preliminary result, the unfiltering seems to be working! *Heads up* some examples are unsafe and inappropriate, this is entirely for the purpose of testing how un-aligned SFT data affect LLM's final output.
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
|
|
|