Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ language:
|
|
| 12 |
|
| 13 |
Reproduce Vicuna, but based on yi-6B.
|
| 14 |
|
| 15 |
-
We can see from some preliminary results,
|
| 16 |
|
| 17 |
**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.
|
| 18 |
|
|
@@ -20,3 +20,5 @@ We can see from some preliminary results, that the unfiltering seems to be worki
|
|
| 20 |
|
| 21 |
|
| 22 |
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
Reproduce Vicuna, but based on yi-6B.
|
| 14 |
|
| 15 |
+
We can see from some preliminary results, the conversation is natural and informative (unsurprisingly), also we observe the unfiltering seems to be working!
|
| 16 |
|
| 17 |
**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.
|
| 18 |
|
|
|
|
| 20 |
|
| 21 |
|
| 22 |
|
| 23 |
+
|
| 24 |
+
|