q4_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K
Browse files
.gitattributes
CHANGED
|
@@ -64,3 +64,4 @@ YugoGPT-Quantized.GGUF.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
|
| 64 |
YugoGPT-Quantized.GGUF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 65 |
YugoGPT-Quantized.GGUF.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 66 |
YugoGPT-Quantized.GGUF.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 64 |
YugoGPT-Quantized.GGUF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 65 |
YugoGPT-Quantized.GGUF.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 66 |
YugoGPT-Quantized.GGUF.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
YugoGPT-Quantized.GGUF.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
YugoGPT-Quantized-GGUF.Q4_K_M.gguf → YugoGPT-Quantized.GGUF.Q4_K_M.gguf
RENAMED
|
File without changes
|