Commit
·
8963e0e
1
Parent(s):
4629b3e
"Update README.md"
Browse files
README.md
CHANGED
@@ -45,6 +45,20 @@ This change primarily affects **Falcon** and **Starcoder** models, with other mo
|
|
45 |
|
46 |
|
47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
# About GGUF format
|
50 |
|
|
|
45 |
|
46 |
|
47 |
|
48 |
+
---
|
49 |
+
# Brief
|
50 |
+
I have a problem with the OpenAssistant falcon *sft* models
|
51 |
+
|
52 |
+
* [falcon-7b-sft-top1-696](https://huggingface.co/OpenAssistant/falcon-7b-sft-top1-696)
|
53 |
+
* [falcon-40b-sft-top1-560](https://huggingface.co/OpenAssistant/falcon-40b-sft-top1-560)
|
54 |
+
* [falcon-40b-sft-mix-1226](https://huggingface.co/OpenAssistant/falcon-40b-sft-mix-1226)
|
55 |
+
|
56 |
+
which currently prevents me from re-quantizing these models. It is not clear to me at the moment if this problem can be solved.
|
57 |
+
|
58 |
+
|
59 |
+
---
|
60 |
+
|
61 |
+
|
62 |
|
63 |
# About GGUF format
|
64 |
|