Commit
•
6155a58
1
Parent(s):
514e2f3
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,6 @@
|
|
| 2 |
license: cc-by-nc-2.0
|
| 3 |
---
|
| 4 |
GGUF importance matrix (imatrix) quants for https://huggingface.co/wolfram/miquliz-120b-v2.0
|
| 5 |
-
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
|
|
|
|
|
|
|
|
|
| 2 |
license: cc-by-nc-2.0
|
| 3 |
---
|
| 4 |
GGUF importance matrix (imatrix) quants for https://huggingface.co/wolfram/miquliz-120b-v2.0
|
| 5 |
+
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
|
| 6 |
+
|
| 7 |
+
Using IQ2_XXS it seems to fit 100/141 layers using 2K context on a 24GB card.
|