Spaces:

Naphula
/

model_tools

Running

App Files Files Community

Naphula commited on 2 days ago

Commit

6b4e63e

verified ·

1 Parent(s): e4ec203

Upload Warlock-7B-v2-Q8_K_XL.txt

Browse files

Files changed (1) hide show

Warlock-7B-v2-Q8_K_XL.txt +1 -0

Warlock-7B-v2-Q8_K_XL.txt ADDED Viewed

	@@ -0,0 +1 @@

+ llama-quantize --tensor-type output.weight=F16 --tensor-type token_embd.weight=F16 --tensor-type "blk\.(0|1|2|30|31)\.attn_k.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.attn_k.weight=Q8_0" --tensor-type "blk\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31)\.attn_output.weight=Q8_0" --tensor-type "blk\.(0|1|2|30|31)\.attn_q.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.attn_q.weight=Q8_0" --tensor-type "blk\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31)\.attn_v.weight=F16" --tensor-type "blk\.(0|1|2|30|31)\.ffn_down.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.ffn_down.weight=Q8_0" --tensor-type "blk\.(0|1|2|30|31)\.ffn_gate.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.ffn_gate.weight=Q8_0" --tensor-type "blk\.(0|1|2|30|31)\.ffn_up.weight=F16" --tensor-type "blk\.(3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29)\.ffn_up.weight=Q8_0" C:\Quanter\outputs\input.gguf C:\Quanter\outputs\output.gguf Q8_0