Hugging Face's logo

quantized4all
/
ggml-oasst-sft-7-llama-30b

Model card Files Community
1
akumaburn commited on
Commit
98cf0e2
•
1 Parent(s): d72e143

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -6,7 +6,8 @@ license:
6
  ---
7
  Model reference: https://huggingface.co/OpenAssistant/oasst-sft-7-llama-30b-xor/
8
 
9
- These ggml model quantizations are modified weights (through the nature of quantization) shared for scientific research and other non-commercial purposes.
 
10
 
11
  The files were archived into parts using 7zip https://www.7-zip.org/
12
 
 
6
  ---
7
  Model reference: https://huggingface.co/OpenAssistant/oasst-sft-7-llama-30b-xor/
8
 
9
+ These ggml model quantizations are modified weights (through the nature of quantization) shared for scientific research and other non-commercial purposes.
10
+ The GGML converted FP16 model is also made available in case you wish to perform your own quantization.
11
 
12
  The files were archived into parts using 7zip https://www.7-zip.org/
13