InferenceIllusionist commited on
Commit
83a2db5
1 Parent(s): 636cfde

Upload Excalibur-7b-DPO-iMat-Q4_K_M.gguf

Browse files

Replacing with new version (~40% less max KL-divergence when quantized using wiki.train.raw)

Files changed (1) hide show
  1. Excalibur-7b-DPO-iMat-Q4_K_M.gguf +3 -0
Excalibur-7b-DPO-iMat-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446b61b693601dc81a79874f9f9176460486151fa92c99cda5fa55dcd98fbf23
3
+ size 4368439072