clarification
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ Cool things I found while playing with it:
|
|
| 18 |
2. When failed, sometimes it tries to reiterate on the problem and try a new approach or fix the mistake.
|
| 19 |
|
| 20 |
Bad things:
|
| 21 |
-
1. It is stupid. Although it's interesting to inspect its chains of thought.
|
| 22 |
2. The final response (after the reasoning chain) is in English.
|
| 23 |
3. Sometimes the model may not produce <|REASONING_END|> which messes up parsing.
|
| 24 |
|
|
|
|
| 18 |
2. When failed, sometimes it tries to reiterate on the problem and try a new approach or fix the mistake.
|
| 19 |
|
| 20 |
Bad things:
|
| 21 |
+
1. It is stupid. Not smarter than the instruct it is based on (not a strict statement, I didn't run any benchmarks yet). Although it's interesting to inspect its chains of thought.
|
| 22 |
2. The final response (after the reasoning chain) is in English.
|
| 23 |
3. Sometimes the model may not produce <|REASONING_END|> which messes up parsing.
|
| 24 |
|