ikawrakow commited on
Commit
6b581ce
1 Parent(s): baa54f2

Adding 2.31-bpw base quantized models

Browse files
llama-v2-13b-2.39bpw.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66809ec037190336b947b8462fd333040dd11f8655b87f018e905b3fd4dd7eb3
3
+ size 3891146752
llama-v2-70b-2.36bpw.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9da2b55f96822b3766f224f14fc0284b933e7bce89df980db65652b62f6cb8
3
+ size 20334162976
llama-v2-7b-2.42bpw.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4648b990066ad862e580426c34da1c2e58860f623a0a57910173fcce28cda03b
3
+ size 2034912832
mistral-7b-2.43bpw.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc68a99f709cc8620ea1178543d6929494639b195cf64967fd70563d94faeb5
3
+ size 2198255232
mixtral-8x7b-2.34bpw.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f125ac2dce20c535024ef95878b7c7fc85c80840c1b7729fd75ac710533e293
3
+ size 13671968512