Update README.md
Browse files
README.md
CHANGED
@@ -12,8 +12,8 @@ inference: false
|
|
12 |
- For q4_2, "Q4_2 ARM #1046" was used. Will update regularly if new changes are made.
|
13 |
- **Choosing between q4_0, q4_1, and q4_2:**
|
14 |
- 4_0 is the fastest. The quality is the poorest.
|
15 |
-
- 4_1 is
|
16 |
-
- 4_2
|
17 |
|
18 |
- 7B version of this can be found here: https://huggingface.co/eachadea/ggml-vicuna-7b-1.1
|
19 |
|
|
|
12 |
- For q4_2, "Q4_2 ARM #1046" was used. Will update regularly if new changes are made.
|
13 |
- **Choosing between q4_0, q4_1, and q4_2:**
|
14 |
- 4_0 is the fastest. The quality is the poorest.
|
15 |
+
- 4_1 is slower. The quality is noticeably better.
|
16 |
+
- 4_2 generally offers the best speed to quality ratio. The drawback is that the format is WIP.
|
17 |
|
18 |
- 7B version of this can be found here: https://huggingface.co/eachadea/ggml-vicuna-7b-1.1
|
19 |
|