GGUF
hermes42 commited on
Commit
6bc10e5
1 Parent(s): 0a58735

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ they need to be manually concaternated via e.g.
12
  cat WizardLM-2-8x22B-imatrix-Q6_K-* > WizardLM-2-8x22B-imatrix-Q6_K.gguf
13
  </code>
14
 
15
- All split files in branch gguf-split uploaded after June 1st, 12:00h GMT can be loaded directly by pointing llama.cpp to the first part, it will load the following parts automagically.
16
 
17
  They can be reassabled to a single file via the gguf-split --merge command, just concaternating as the UNIX split files WON'T WORK.
18
 
 
12
  cat WizardLM-2-8x22B-imatrix-Q6_K-* > WizardLM-2-8x22B-imatrix-Q6_K.gguf
13
  </code>
14
 
15
+ All split files in branch <a href=https://huggingface.co/hermes42/WizardLM-2-8x22B-imatrix-GGUF/tree/gguf-split>gguf-split</a> uploaded after June 1st, 12:00h GMT can be loaded directly by pointing llama.cpp to the first part, it will load the following parts automagically.
16
 
17
  They can be reassabled to a single file via the gguf-split --merge command, just concaternating as the UNIX split files WON'T WORK.
18