Status update 2026-11-14: first SFT attempt did not pass blind evaluation; no weights released
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ tags:
|
|
| 20 |
|
| 21 |
## Status
|
| 22 |
|
| 23 |
-
**
|
| 24 |
|
| 25 |
The intended task is assistant conversation and instruction following in Polish and English. The intended use is research; this snapshot does not establish conversational quality, a quality improvement over the base, or suitability for production.
|
| 26 |
|
|
|
|
| 20 |
|
| 21 |
## Status
|
| 22 |
|
| 23 |
+
**Status update: 14 November 2026.** A first supervised fine-tuning attempt (public data only) was trained and did not pass our blind evaluation against the base model; no instruct weights are released.
|
| 24 |
|
| 25 |
The intended task is assistant conversation and instruction following in Polish and English. The intended use is research; this snapshot does not establish conversational quality, a quality improvement over the base, or suitability for production.
|
| 26 |
|