Hugging Face's logo

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

GGUF
Model card Files Community
nisten commited on
Commit
3107dcd
•
1 Parent(s): 8d80a92

very good quant for speed/perplexity, embedding is at q4k

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. qwen7bv2inst_q4km_output8bit.gguf → qwen7bv2inst_q4km_embedding4k_output8bit.gguf +0 -0
.gitattributes CHANGED
@@ -57,3 +57,4 @@ qwen7bv2inst_Iq4xs_output6k.gguf filter=lfs diff=lfs merge=lfs -text
57
  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
 
 
57
  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
qwen7bv2inst_q4km_output8bit.gguf → qwen7bv2inst_q4km_embedding4k_output8bit.gguf RENAMED
File without changes