shaowenchen
commited on
Commit
•
c2e1b2f
1
Parent(s):
71af746
Update README.md
Browse files
README.md
CHANGED
@@ -45,11 +45,15 @@ docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/ggu
|
|
45 |
|
46 |
## Provided images
|
47 |
|
48 |
-
| Name | Quant method | Size
|
49 |
-
| --------------------------------------- | ------------ |
|
50 |
-
| `shaowenchen/vicuna-33b-v1.3-gguf:Q2_K` | Q2_K |
|
51 |
-
| `shaowenchen/vicuna-33b-v1.3-gguf:Q3_K` | Q3_K |
|
52 |
-
| `shaowenchen/vicuna-33b-v1.3-gguf:Q4_K` | Q4_K |
|
|
|
|
|
|
|
|
|
53 |
|
54 |
Usage:
|
55 |
|
|
|
45 |
|
46 |
## Provided images
|
47 |
|
48 |
+
| Name | Quant method | Compressed Size |
|
49 |
+
| --------------------------------------- | ------------ | --------------- |
|
50 |
+
| `shaowenchen/vicuna-33b-v1.3-gguf:Q2_K` | Q2_K | 12.78 GB |
|
51 |
+
| `shaowenchen/vicuna-33b-v1.3-gguf:Q3_K` | Q3_K | 14.81 GB |
|
52 |
+
| `shaowenchen/vicuna-33b-v1.3-gguf:Q4_K` | Q4_K | 18.24 GB |
|
53 |
+
| `shaowenchen/vicuna-33b-v1.3-gguf:Q5_K` | Q5_K | 21.72 GB |
|
54 |
+
| `shaowenchen/vicuna-33b-v1.3-gguf:Q6_K` | Q6_K | 25.05 GB |
|
55 |
+
| `shaowenchen/vicuna-33b-v1.3-gguf:Q8_0` | Q8_0 | 31.34 GB |
|
56 |
+
| `shaowenchen/vicuna-33b-v1.3-gguf:full` | full | 56.07 GB |
|
57 |
|
58 |
Usage:
|
59 |
|