jartine commited on
Commit
052c7c7
1 Parent(s): 3480d41

Quantize Meta-Llama-3-70B-Instruct with llamafile-0.7.3 Q2_K

Browse files
.gitattributes CHANGED
@@ -40,3 +40,4 @@ Meta-Llama-3-70B-Instruct.F16.llamafile.cat1 filter=lfs diff=lfs merge=lfs -text
40
  Meta-Llama-3-70B-Instruct.F16.llamafile.cat2 filter=lfs diff=lfs merge=lfs -text
41
  Meta-Llama-3-70B-Instruct.Q8_0.llamafile.cat0 filter=lfs diff=lfs merge=lfs -text
42
  Meta-Llama-3-70B-Instruct.Q8_0.llamafile.cat1 filter=lfs diff=lfs merge=lfs -text
 
 
40
  Meta-Llama-3-70B-Instruct.F16.llamafile.cat2 filter=lfs diff=lfs merge=lfs -text
41
  Meta-Llama-3-70B-Instruct.Q8_0.llamafile.cat0 filter=lfs diff=lfs merge=lfs -text
42
  Meta-Llama-3-70B-Instruct.Q8_0.llamafile.cat1 filter=lfs diff=lfs merge=lfs -text
43
+ Meta-Llama-3-70B-Instruct.Q2_K.llamafile filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-70B-Instruct.Q2_K.llamafile ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145eb5881392bd2e485ccc5b4f0b3c601f4fdce3c7b50fcc2fc083e37537cc39
3
+ size 26400068194