Transformers
mpt
Composer
MosaicML
llm-foundry
TheBloke commited on
Commit
d39a0a3
1 Parent(s): bb2e6f5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -5
README.md CHANGED
@@ -39,11 +39,7 @@ Please note that these GGMLs are **not compatible with llama.cpp, or currently w
39
 
40
  [KoboldCpp](https://github.com/LostRuins/koboldcpp) just added GPU accelerated (OpenCL) support for MPT models, so that is the client I recommend using for these models.
41
 
42
- **Note**: There is currently a bug with loading this model in KoboldCpp Release 1.32: it will wrongly detect it as a GPT-NeoX model.
43
-
44
- To resolve this, add argument `--forceversion 500`
45
-
46
- This should be fixed in the next release of KoboldCpp, so if you are running a version later than 1.32 it should not be necessary.
47
 
48
  ## Repositories available
49
 
 
39
 
40
  [KoboldCpp](https://github.com/LostRuins/koboldcpp) just added GPU accelerated (OpenCL) support for MPT models, so that is the client I recommend using for these models.
41
 
42
+ **Note**: Please use version 1.32.1 or later of KoboldCpp, as there was a bug in 1.32 that affected loading of MPT models.
 
 
 
 
43
 
44
  ## Repositories available
45