Commit
•
7dcf61c
1
Parent(s):
0e12e9d
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,8 +15,8 @@ Retrained and merged using updated LoRAs.
|
|
| 15 |
To merge and convert, used:
|
| 16 |
```
|
| 17 |
transformers 4.28.1.
|
| 18 |
-
gptq
|
| 19 |
-
llamacpp master branch
|
| 20 |
```
|
| 21 |
|
| 22 |
Notes for usage.
|
|
@@ -28,7 +28,7 @@ Notes for usage.
|
|
| 28 |
|
| 29 |
Currently transferring models over.
|
| 30 |
```
|
| 31 |
-
7B safetensors 4bit -
|
| 32 |
7B ggml 4bit -
|
| 33 |
|
| 34 |
13B safetensors 4bit -
|
|
|
|
| 15 |
To merge and convert, used:
|
| 16 |
```
|
| 17 |
transformers 4.28.1.
|
| 18 |
+
gptq cuda branch 5731aa1
|
| 19 |
+
llamacpp master branch 8944a13
|
| 20 |
```
|
| 21 |
|
| 22 |
Notes for usage.
|
|
|
|
| 28 |
|
| 29 |
Currently transferring models over.
|
| 30 |
```
|
| 31 |
+
7B safetensors 4bit -
|
| 32 |
7B ggml 4bit -
|
| 33 |
|
| 34 |
13B safetensors 4bit -
|