Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,8 @@ license: mit
|
|
| 3 |
base_model:
|
| 4 |
- ServiceNow-AI/Apriel-Nemotron-15b-Thinker
|
| 5 |
---
|
| 6 |
-
imatrix GGUF quants
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
base_model:
|
| 4 |
- ServiceNow-AI/Apriel-Nemotron-15b-Thinker
|
| 5 |
---
|
| 6 |
+
imatrix GGUF quants
|
| 7 |
+
|
| 8 |
+
Execution tips from my private experience:
|
| 9 |
+
* don't quantize context
|
| 10 |
+
* use top_p 0.9, top_k 20, temp 0.6, min_p 0.05
|