Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ Based on our latest technological advancements, we have trained a `GLM-4-0414` s
|
|
| 20 |
| ------------ | ----------------- | -------------------------------------------- |
|
| 21 |
| temperature | **0.6** | Balances creativity and stability |
|
| 22 |
| top_p | **0.95** | Cumulative probability threshold for sampling|
|
| 23 |
-
| top_k | **
|
| 24 |
| max_new_tokens | **30000** | Leaves enough tokens for thinking |
|
| 25 |
|
| 26 |
### II. Enforced Thinking
|
|
|
|
| 20 |
| ------------ | ----------------- | -------------------------------------------- |
|
| 21 |
| temperature | **0.6** | Balances creativity and stability |
|
| 22 |
| top_p | **0.95** | Cumulative probability threshold for sampling|
|
| 23 |
+
| top_k | **40** | Filters out rare tokens while maintaining diversity |
|
| 24 |
| max_new_tokens | **30000** | Leaves enough tokens for thinking |
|
| 25 |
|
| 26 |
### II. Enforced Thinking
|