jartine commited on
Commit
7dd9c2f
1 Parent(s): 6469062

Quantize mistral-7b-instruct-v0.2 with llamafile-0.7 Q4_K

Browse files
.gitattributes CHANGED
@@ -60,3 +60,4 @@ mistral-7b-instruct-v0.2.Q8_0.llamafile filter=lfs diff=lfs merge=lfs -text
60
  mistral-7b-instruct-v0.2.Q4_1.llamafile filter=lfs diff=lfs merge=lfs -text
61
  mistral-7b-instruct-v0.2.Q5_1.llamafile filter=lfs diff=lfs merge=lfs -text
62
  mistral-7b-instruct-v0.2.Q3_K.llamafile filter=lfs diff=lfs merge=lfs -text
 
 
60
  mistral-7b-instruct-v0.2.Q4_1.llamafile filter=lfs diff=lfs merge=lfs -text
61
  mistral-7b-instruct-v0.2.Q5_1.llamafile filter=lfs diff=lfs merge=lfs -text
62
  mistral-7b-instruct-v0.2.Q3_K.llamafile filter=lfs diff=lfs merge=lfs -text
63
+ mistral-7b-instruct-v0.2.Q4_K.llamafile filter=lfs diff=lfs merge=lfs -text
mistral-7b-instruct-v0.2.Q4_K.llamafile ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea60127c9e6b852c7fbe88a35cb50ae015d6445cd65e02611a4ecdaac4159e2
3
+ size 4392751599