Hugging Face's logo

nisten
/
qwenv2-7b-inst-imatrix-gguf

GGUF
Model card Files Community
nisten commited on
Commit
51abeba
•
1 Parent(s): 3107dcd

standard iq4xs imatrix quant from bf16 gguf so it has better perplexity

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. qwen7bv2inst_iq4xs_output6k.gguf → qwen7bv2inst_iq4xs_embedding4xs_output6k.gguf +0 -0
.gitattributes CHANGED
@@ -58,3 +58,4 @@ qwen7bv2instruct_q8.gguf filter=lfs diff=lfs merge=lfs -text
58
  qwen7bv2inst_q4km_embeddingf16_outputf16.gguf filter=lfs diff=lfs merge=lfs -text
59
  qwen7bv2inst_iq4xs_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
60
  qwen7bv2inst_q4km_embedding4k_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
 
 
58
  qwen7bv2inst_q4km_embeddingf16_outputf16.gguf filter=lfs diff=lfs merge=lfs -text
59
  qwen7bv2inst_iq4xs_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
60
  qwen7bv2inst_q4km_embedding4k_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
61
+ qwen7bv2inst_iq4xs_embedding4xs_output6k.gguf filter=lfs diff=lfs merge=lfs -text
qwen7bv2inst_iq4xs_output6k.gguf → qwen7bv2inst_iq4xs_embedding4xs_output6k.gguf RENAMED
File without changes