Commit History

Rename qwen7bf16.gguf to qwen7bv2instruct_bf16.gguf
9cbd6f2
verified

nisten commited on

very good quant for speed/perplexity, embedding is at q4k
6c5e613
verified

nisten commited on

Probably best speed to perplexity ratio of any 7b gguf model so far
0e76852
verified

nisten commited on

standard q5km conversions with 8bit output for reference.
6da7eb9
verified

nisten commited on

Good conversion from bf16 down instead of from f16
957d5fb
verified

nisten commited on

calculated imatrix in 8bit, was jsut as good as f16 imatrix
b7097b6
verified

nisten commited on

Rename qwen7bq4xs.gguf to qwen7bq4xsoutput6k.gguf
6e41799
verified

nisten commited on

Rename qwen7bq4xsembedding5bitkoutput8bit.gguf to qwen7bq4xsembedding8output8.gguf
ee4c789
verified

nisten commited on

Rename qwen7bq4kembeddingbf16outputbf16.gguf to qwen7bq4kembeddingf16outputf16.gguf
d9150dc
verified

nisten commited on

Upload 9 files
49deabb
verified

nisten commited on

Update README.md
081ce53
verified

nisten commited on

Update README.md
357d311
verified

nisten commited on

initial commit
2909ebc
verified

nisten commited on