Initial GGML model commit
Browse files
README.md
CHANGED
|
@@ -28,6 +28,11 @@ I have quantised the GGML files in this repo with the latest version. Therefore
|
|
| 28 |
## Provided files
|
| 29 |
| Name | Quant method | Bits | Size | RAM required | Use case |
|
| 30 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
|
| 33 |
## How to run in `llama.cpp`
|
|
|
|
| 28 |
## Provided files
|
| 29 |
| Name | Quant method | Bits | Size | RAM required | Use case |
|
| 30 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
| 31 |
+
| guanaco-13B.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB | 9.82 GB | 4-bit. |
|
| 32 |
+
| guanaco-13B.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB | 10.64 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
|
| 33 |
+
| guanaco-13B.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB | 11.45 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
|
| 34 |
+
| guanaco-13B.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB | 12.26 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
|
| 35 |
+
| guanaco-13B.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB | 16.33 GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
|
| 36 |
|
| 37 |
|
| 38 |
## How to run in `llama.cpp`
|