Update GPTQ to v2 of model which fixes some errors in training.
Browse files
Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d16a7c66043c61cb6133837e154713a478bd26866789c5d3e5bfe8ce55a77b2
|
| 3 |
+
size 8110988222
|
huggingface-metadata.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
url: https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ
|
| 2 |
+
branch: main
|
| 3 |
+
download date: 2023-05-17 16:35:36
|
| 4 |
+
sha256sum:
|
| 5 |
+
5acd7195dbe3826d44e77d5184d3f0b29ac0add2f77a4b3f6f848d301fc797c5 Wizard-Vicuna-13B-Uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors
|
| 6 |
+
9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model
|