Probably best speed to perplexity ratio of any 7b gguf model so far
Browse files
.gitattributes
CHANGED
|
@@ -48,3 +48,4 @@ qwen7bq4xsoutput6k.gguf filter=lfs diff=lfs merge=lfs -text
|
|
| 48 |
8bitimatrix.dat filter=lfs diff=lfs merge=lfs -text
|
| 49 |
qwenv2instruct7b_q8.gguf filter=lfs diff=lfs merge=lfs -text
|
| 50 |
qwen7bv2instruct_q5km.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 48 |
8bitimatrix.dat filter=lfs diff=lfs merge=lfs -text
|
| 49 |
qwenv2instruct7b_q8.gguf filter=lfs diff=lfs merge=lfs -text
|
| 50 |
qwen7bv2instruct_q5km.gguf filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
qwen7bv2_iq4xs_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
|
qwen7bq4xsoutput8bit.gguf → qwen7bv2_iq4xs_output8bit.gguf
RENAMED
|
File without changes
|