Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,9 @@
|
|
| 1 |
Mistral (Non-Tekken), i.e., Mistral v3 + `[SYSTEM_PROMPT]`
|
| 2 |
|
| 3 |
-
Looks like `<think>` doesn't need to be prefilled.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
Yes, this is how much I want to avoid tuning MoEs.
|
|
|
|
| 1 |
Mistral (Non-Tekken), i.e., Mistral v3 + `[SYSTEM_PROMPT]`
|
| 2 |
|
| 3 |
+
Looks like `<think>` doesn't need to be prefilled.
|
| 4 |
+
|
| 5 |
+
No toxic data so you may want to prefill / guide reasoning when dealing with heavy themes (unless your prompt is sufficiently instructed/gaslit to be evil).
|
| 6 |
+
|
| 7 |
+
Alternatively, since `<think>` is not a special token, you can influence reasoning by phrasing it like `<evil_think>`, `<creative_think>`, or `<spicy_think>`, etc. It's smart enough to close it properly.
|
| 8 |
|
| 9 |
Yes, this is how much I want to avoid tuning MoEs.
|