Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ This is GGML format quantised 4-bit, 5-bit and 8-bit [MosaicML's MPT-7B-Storywri
|
|
| 16 |
|
| 17 |
This repo is the result of converting to GGML and quantising.
|
| 18 |
|
|
|
|
|
|
|
| 19 |
## Repositories available
|
| 20 |
|
| 21 |
* [MPT-7B: 4-bit, 5-bit and 8-bit GGML models for CPU (+CUDA) inference](https://huggingface.co/TheBloke/MPT-7B-GGML).
|
|
|
|
| 16 |
|
| 17 |
This repo is the result of converting to GGML and quantising.
|
| 18 |
|
| 19 |
+
Please note that these MPT GGMLs are **not compatbile with llama.cpp**. Right now they can only be used in a couple of tools. This is bound to improve in the near future.
|
| 20 |
+
|
| 21 |
## Repositories available
|
| 22 |
|
| 23 |
* [MPT-7B: 4-bit, 5-bit and 8-bit GGML models for CPU (+CUDA) inference](https://huggingface.co/TheBloke/MPT-7B-GGML).
|