Update README.md
Browse files
README.md
CHANGED
|
@@ -53,7 +53,7 @@ All generated locally and pretty quickly too! 😲 Due to our very limited resou
|
|
| 53 |
|
| 54 |
# 🧀 Information
|
| 55 |
- ⚠️ A low temperature must be used to ensure it won't fail at reasoning. we use 0.3 - 0.8!
|
| 56 |
-
- ⚠️ Due to the current prompt format, it may sometimes put <|FinalAnswer|> at the end, you can ignore this or modify the prompt format.
|
| 57 |
- this is out flagship model, with top-tier reasoning, rivaling gemini-flash-exp-2.0-thinking and o1 mini. results are overall similar to both of them, we are not comparing to qwq as it has much longer results which waste tokens.
|
| 58 |
|
| 59 |
# 🧀 Uploaded model
|
|
|
|
| 53 |
|
| 54 |
# 🧀 Information
|
| 55 |
- ⚠️ A low temperature must be used to ensure it won't fail at reasoning. we use 0.3 - 0.8!
|
| 56 |
+
- ⚠️ Due to the current prompt format, it may sometimes put <|FinalAnswer|> without providing a final answer at the end, you can ignore this or modify the prompt format.
|
| 57 |
- this is out flagship model, with top-tier reasoning, rivaling gemini-flash-exp-2.0-thinking and o1 mini. results are overall similar to both of them, we are not comparing to qwq as it has much longer results which waste tokens.
|
| 58 |
|
| 59 |
# 🧀 Uploaded model
|