Transformers
llamafile
English
stablelm
jartine commited on
Commit
5502620
1 Parent(s): 7bc461c

Quantize rocket-3B with llamafile-0.7.3 Q4_1

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. rocket-3b.Q4_1.llamafile +3 -0
.gitattributes CHANGED
@@ -59,3 +59,4 @@ rocket-3b.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
59
  rocket-3b.Q8_0.llamafile filter=lfs diff=lfs merge=lfs -text
60
  rocket-3b.F16.llamafile filter=lfs diff=lfs merge=lfs -text
61
  rocket-3b.BF16.llamafile filter=lfs diff=lfs merge=lfs -text
 
 
59
  rocket-3b.Q8_0.llamafile filter=lfs diff=lfs merge=lfs -text
60
  rocket-3b.F16.llamafile filter=lfs diff=lfs merge=lfs -text
61
  rocket-3b.BF16.llamafile filter=lfs diff=lfs merge=lfs -text
62
+ rocket-3b.Q4_1.llamafile filter=lfs diff=lfs merge=lfs -text
rocket-3b.Q4_1.llamafile ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4586cf39f05f0a803b2b0ed9e3a1ea42cbb652950ad65ac50e7698a81f14ea5f
3
+ size 1799557580