Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ This is GGML format quantised 4-bit, 5-bit and 8-bit GGML models of [MosaicML's
|
|
| 20 |
|
| 21 |
This repo is the result of converting to GGML and quantising.
|
| 22 |
|
| 23 |
-
Please note that these MPT GGMLs are **not compatbile with llama.cpp**.
|
| 24 |
|
| 25 |
## Repositories available
|
| 26 |
|
|
@@ -43,8 +43,10 @@ Please note that these MPT GGMLs are **not compatbile with llama.cpp**. Right no
|
|
| 43 |
These files are **not** compatible with llama.cpp.
|
| 44 |
|
| 45 |
Currently they can be used with:
|
| 46 |
-
* The
|
|
|
|
| 47 |
* [rustformers' llm](https://github.com/rustformers/llm)
|
|
|
|
| 48 |
|
| 49 |
As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)
|
| 50 |
|
|
|
|
| 20 |
|
| 21 |
This repo is the result of converting to GGML and quantising.
|
| 22 |
|
| 23 |
+
Please note that these MPT GGMLs are **not compatbile with llama.cpp**. See below for software that works with these models.
|
| 24 |
|
| 25 |
## Repositories available
|
| 26 |
|
|
|
|
| 43 |
These files are **not** compatible with llama.cpp.
|
| 44 |
|
| 45 |
Currently they can be used with:
|
| 46 |
+
* The ctransformers Python library: [ctransformers](https://github.com/marella/ctransformers)
|
| 47 |
+
* The GPT4All-UI which uses ctransformers: [GPT4All-UI](https://github.com/nomic-ai/gpt4all-ui)
|
| 48 |
* [rustformers' llm](https://github.com/rustformers/llm)
|
| 49 |
+
* The example `mpt` binary provided with [ggml](https://github.com/ggerganov/ggml)
|
| 50 |
|
| 51 |
As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)
|
| 52 |
|