jartine commited on
Commit
2b6b78c
1 Parent(s): 27eb810

Quantize Q8_0 with llamafile-0.8.7

Browse files
Mistral-7B-Instruct-v0.3.Q8_0.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f9ee0ca5f9880dcba737345abeceb20420e7892c88b96a3f844b140beb2bc9b
3
- size 7738112171
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ccf804f6f45ad751a0f0fc9500230b27f2b1cced25f8e359bb8bb9b06d54b1f
3
+ size 7728281772