Upload mmproj-Qwen2-VL-2B-Instruct-f16.gguf
Browse filesMore 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 +1 -0
- mmproj-Qwen2-VL-2B-Instruct-f16.gguf +3 -0
.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
|