qwp4w3hyb
/

Qwen2-7B-Instruct-iMat-GGUF

Text Generation

Model card Files Files and versions Community

qwp4w3hyb commited on Jun 7

Commit

1f2d797

•

1 Parent(s): 9827302

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -10,7 +10,6 @@ base_model: Qwen/Qwen2-7B-Instruct
 # Quant Infos
-- Includes tokenizer fixes that were bugged in the initial version
 - quants done with an importance matrix for improved quantization loss
 - ggufs & imatrix generated from bf16 for "optimal" accuracy loss
 - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S

 # Quant Infos
 - quants done with an importance matrix for improved quantization loss
 - ggufs & imatrix generated from bf16 for "optimal" accuracy loss
 - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S