Correctly format developer attribution in README.md
Browse files
README.md
CHANGED
|
@@ -22,4 +22,4 @@ Draft model trained on 365k synthetic examples. Full 500k model in progress.
|
|
| 22 |
Decoder-only transformer | ~20M params | 8k BPE vocab | 256 max tokens
|
| 23 |
|
| 24 |
## Safety
|
| 25 |
-
Trained to decline out-of-scope questions. Low temperature (0.4) at inference.
|
|
|
|
| 22 |
Decoder-only transformer | ~20M params | 8k BPE vocab | 256 max tokens
|
| 23 |
|
| 24 |
## Safety
|
| 25 |
+
Trained to decline out-of-scope questions. Low temperature (0.4) at inference.
|