Hugging Face's logo

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

GGUF
Inference Endpoints
conversational
Model card Files Community
nisten commited on
Commit
bc0fa51
•
1 Parent(s): bb46d3a

Best q8 conversion down from bf16 with slightly better perplexity than f16 based quants

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. qwenv2instruct7b_q8.gguf → qwen7bv2instruct_q8.gguf +0 -0
.gitattributes CHANGED
@@ -54,3 +54,4 @@ 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
56
  qwen7bv2inst_Iq4xs_output6k.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
56
  qwen7bv2inst_Iq4xs_output6k.gguf filter=lfs diff=lfs merge=lfs -text
57
+ qwen7bv2instruct_q8.gguf filter=lfs diff=lfs merge=lfs -text
qwenv2instruct7b_q8.gguf → qwen7bv2instruct_q8.gguf RENAMED
File without changes