mradermacher
commited on
Commit
•
66b08ae
1
Parent(s):
96739e9
Update README.md
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ quantized_by: mradermacher
|
|
10 |
|
11 |
weighted/imatrix quants of https://huggingface.co/davidkim205/Rhea-72b-v0.5
|
12 |
|
13 |
-
**the imatrix was calculated on a reduced 40k token set as the full token set caused overflows in the model (likely a model bug)**
|
14 |
|
15 |
<!-- provided-files -->
|
16 |
static quants are available at https://huggingface.co/mradermacher/Rhea-72b-v0.5-GGUF
|
|
|
10 |
|
11 |
weighted/imatrix quants of https://huggingface.co/davidkim205/Rhea-72b-v0.5
|
12 |
|
13 |
+
**the imatrix was calculated on a reduced 40k token set (the "quarter" set) as the full token set caused overflows in the model (likely a model bug)**
|
14 |
|
15 |
<!-- provided-files -->
|
16 |
static quants are available at https://huggingface.co/mradermacher/Rhea-72b-v0.5-GGUF
|