l3utterfly commited on
Commit
7d91d3b
·
1 Parent(s): ca2d54c

Add PTE files for context sizes 2048, 4096, 8192

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.pte filter=lfs diff=lfs merge=lfs -text
Llama-3-8B-Stroganoff_kv2_sdpa_xnn_qe_4_32_ctx2048.pte ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50b492a4175a24c5a188dc040b64bac2d5ccdc5e57de27724e448babb637dc1
3
+ size 4169560736
Llama-3-8B-Stroganoff_kv2_sdpa_xnn_qe_4_32_ctx4096.pte ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5365acc7f8addaa1bed91298fff5c19cafd312afa451f1facbd4837574a9d595
3
+ size 4171657888
Llama-3-8B-Stroganoff_kv2_sdpa_xnn_qe_4_32_ctx8192.pte ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1417555871d270bc16db9e2a35357f145018018c690e7bb215f78e35037001
3
+ size 4175852192