Hugging Face's logo

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

GGUF
Inference Endpoints
conversational
Model card Files Community
nisten commited on
Commit
0bc4249
•
1 Parent(s): 9b91d66

great quant if your chip has 8bit acceleration, slightly better than 4k embedding

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. qwen7bv2inst_iq4xs_embedding8_output8.gguf → qwen7bv2inst_iq4xs_embedding8_outputq8.gguf +0 -0
.gitattributes CHANGED
@@ -52,3 +52,4 @@ qwen7bv2_iq4xs_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
52
  qwen7bv2inst_q4km_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
53
  qwen7bv2instruct_bf16.gguf filter=lfs diff=lfs merge=lfs -text
54
  qwen7bv2inst_iq4xs_embedding8_output8.gguf filter=lfs diff=lfs merge=lfs -text
 
 
52
  qwen7bv2inst_q4km_output8bit.gguf filter=lfs diff=lfs merge=lfs -text
53
  qwen7bv2instruct_bf16.gguf filter=lfs diff=lfs merge=lfs -text
54
  qwen7bv2inst_iq4xs_embedding8_output8.gguf filter=lfs diff=lfs merge=lfs -text
55
+ qwen7bv2inst_iq4xs_embedding8_outputq8.gguf filter=lfs diff=lfs merge=lfs -text
qwen7bv2inst_iq4xs_embedding8_output8.gguf → qwen7bv2inst_iq4xs_embedding8_outputq8.gguf RENAMED
File without changes