TheBloke commited on
Commit
41d2a48
1 Parent(s): bde0031

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
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**. Right now they can only be used in a couple of tools. This is bound to improve in the near future.
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 example `mpt` binary provided with [ggml](https://github.com/ggerganov/ggml)
 
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