GGUF
Inference Endpoints
sakuraumi commited on
Commit
4ec969e
1 Parent(s): 14b623e

Upload sakura-7b-lnovel-v0.9-Q4KM_awq4bit.gguf

Browse files
.gitattributes CHANGED
@@ -40,3 +40,4 @@ sakura-7b-lnovel-v0.9-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
  sakura-7b-lnovel-v0.9-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
41
  sakura-7b-lnovel-v0.9-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
42
  sakura-7b-lnovel-v0.9-fp16.gguf filter=lfs diff=lfs merge=lfs -text
 
 
40
  sakura-7b-lnovel-v0.9-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
41
  sakura-7b-lnovel-v0.9-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
42
  sakura-7b-lnovel-v0.9-fp16.gguf filter=lfs diff=lfs merge=lfs -text
43
+ sakura-7b-lnovel-v0.9-Q4KM_awq4bit.gguf filter=lfs diff=lfs merge=lfs -text
sakura-7b-lnovel-v0.9-Q4KM_awq4bit.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3dd272f18c5bd000e46e851787d0083749996927a435ae4eac9ac1b2e9a360
3
+ size 4899217920