Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,8 @@ inference: false
|
|
| 8 |
- 4-bit quantized
|
| 9 |
- Based on version 1.1
|
| 10 |
- Used PR "More accurate Q4_0 and Q4_1 quantizations #896" (should be closer in quality to unquantized)
|
|
|
|
|
|
|
| 11 |
|
| 12 |
- 7B version of this can be found here: https://huggingface.co/eachadea/ggml-vicuna-7b-1.1
|
| 13 |
|
|
|
|
| 8 |
- 4-bit quantized
|
| 9 |
- Based on version 1.1
|
| 10 |
- Used PR "More accurate Q4_0 and Q4_1 quantizations #896" (should be closer in quality to unquantized)
|
| 11 |
+
- Choosing between q4_0 and q4_1, the logic of higher number \= better does not apply. If you are confused, stick with q4_0.
|
| 12 |
+
|
| 13 |
|
| 14 |
- 7B version of this can be found here: https://huggingface.co/eachadea/ggml-vicuna-7b-1.1
|
| 15 |
|