q5_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K
Browse files
.gitattributes
CHANGED
|
@@ -38,3 +38,4 @@ Yugo45A-GPT-Quantized-GGUF.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
|
| 38 |
Yugo45A-GPT-Quantized-GGUF-unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
Yugo45A-GPT-Quantized-GGUF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
Yugo45A-GPT-Quantized-GGUF-unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 38 |
Yugo45A-GPT-Quantized-GGUF-unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
Yugo45A-GPT-Quantized-GGUF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
Yugo45A-GPT-Quantized-GGUF-unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Yugo45A-GPT-Quantized-GGUF.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
Yugo45A-GPT-Quantized-GGUF-unsloth.Q5_K_M.gguf → Yugo45A-GPT-Quantized-GGUF.Q5_K_M.gguf
RENAMED
|
File without changes
|