stduhpf commited on
Commit
e568caa
·
verified ·
1 Parent(s): a241d70

Upload mmproj-Qwen2-VL-2B-Instruct-f16.gguf

Browse files

More options for mmproj quantization would be better, I think. F32 mmproj is still fairly large, and from my limited testing, f16 seem to perform perfectly fine.

.gitattributes CHANGED
@@ -57,3 +57,4 @@ Qwen2-VL-2B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
57
  Qwen2-VL-2B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
58
  Qwen2-VL-2B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text
59
  mmproj-Qwen2-VL-2B-Instruct-f32.gguf filter=lfs diff=lfs merge=lfs -text
 
 
57
  Qwen2-VL-2B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
58
  Qwen2-VL-2B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text
59
  mmproj-Qwen2-VL-2B-Instruct-f32.gguf filter=lfs diff=lfs merge=lfs -text
60
+ mmproj-Qwen2-VL-2B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
mmproj-Qwen2-VL-2B-Instruct-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b160fd199d84c17b25093c47ba0b4119f46f030d23f63e6716e91a88c9f3cd6
3
+ size 1331656192