Commit
·
4309fd8
1
Parent(s):
6c833db
"Update README.md"
Browse files
README.md
CHANGED
|
@@ -37,6 +37,20 @@ This change primarily affects **Falcon** and **Starcoder** models, with other mo
|
|
| 37 |
|
| 38 |
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
# About GGUF format
|
| 42 |
|
|
|
|
| 37 |
|
| 38 |
|
| 39 |
|
| 40 |
+
---
|
| 41 |
+
# Brief
|
| 42 |
+
I have a problem with the OpenAssistant falcon *sft* models
|
| 43 |
+
|
| 44 |
+
* [falcon-7b-sft-top1-696](https://huggingface.co/OpenAssistant/falcon-7b-sft-top1-696)
|
| 45 |
+
* [falcon-40b-sft-top1-560](https://huggingface.co/OpenAssistant/falcon-40b-sft-top1-560)
|
| 46 |
+
* [falcon-40b-sft-mix-1226](https://huggingface.co/OpenAssistant/falcon-40b-sft-mix-1226)
|
| 47 |
+
|
| 48 |
+
which currently prevents me from re-quantizing these models. It is not clear to me at the moment if this problem can be solved.
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
---
|
| 52 |
+
|
| 53 |
+
|
| 54 |
|
| 55 |
# About GGUF format
|
| 56 |
|