Commit
•
ca373c5
1
Parent(s):
5908ed3
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,13 @@ Time taken: 19.0 mins
|
|
| 38 |
|
| 39 |
GGUF versions are available [here](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo-GGUF)
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
## Chat Template
|
| 42 |
|
| 43 |
This was my process during fine tune to realign the prompt template to chatML. There seems to be an error where you can use either Mistral (original) prompt template
|
|
|
|
| 38 |
|
| 39 |
GGUF versions are available [here](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo-GGUF)
|
| 40 |
|
| 41 |
+
# ExLlamav2
|
| 42 |
+
|
| 43 |
+
Thanks to user [bartowski](https://huggingface.co/bartowski) we now have exllamav2 quantizations in 3.5 through 8 bpw. They are available here:
|
| 44 |
+
|
| 45 |
+
+ [bartowski/WestLake-7B-v2-laser-truthy-dpo-exl2](https://huggingface.co/bartowski/WestLake-7B-v2-laser-truthy-dpo-exl2)
|
| 46 |
+
|
| 47 |
+
|
| 48 |
## Chat Template
|
| 49 |
|
| 50 |
This was my process during fine tune to realign the prompt template to chatML. There seems to be an error where you can use either Mistral (original) prompt template
|