Hugging Face's logo

datatab
/
YugoGPT-Quantized-GGUF

Transformers
GGUF
Serbian
mistral
text-generation-inference
Inference Endpoints
Model card Files Community
datatab commited on
Commit
5e97c4c
•
1 Parent(s): a08886e

q5_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. YugoGPT-Quantized-GGUF.Q5_K_M.gguf → YugoGPT-Quantized.GGUF.Q5_K_M.gguf +0 -0
.gitattributes CHANGED
@@ -67,3 +67,4 @@ 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
68
  YugoGPT-Quantized.GGUF.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
69
  YugoGPT-Quantized.GGUF.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
 
 
67
  YugoGPT-Quantized.GGUF.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
68
  YugoGPT-Quantized.GGUF.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
69
  YugoGPT-Quantized.GGUF.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
70
+ YugoGPT-Quantized.GGUF.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
YugoGPT-Quantized-GGUF.Q5_K_M.gguf → YugoGPT-Quantized.GGUF.Q5_K_M.gguf RENAMED
File without changes