Nexesenex
/

Meta_Llama-3.1-8b-it_iMat_Custom_Quant_Stategies-GGUF

Inference Endpoints

Model card Files Files and versions Community

Nexesenex commited on Aug 19

Commit

2e13fc3

•

1 Parent(s): b0882d3

Update README.md

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -23,9 +23,9 @@ Master
 Size : 3.04 GiB (3.25 BPW)
 PPL 512 wikitext : 8.4985 +/- 0.05402
-PR (bad)
-Size : 3.11 GiB (3.33 BPW)
-PPL 512 wikitext : 8.4027 +/- 0.05263
 IQ3_XS
@@ -33,15 +33,15 @@ Master
 Size : 3.27 GiB (3.50 BPW)
 PPL 512 wikitext : 8.2019 +/- 0.05167
-PR (so so)
-Size : 3.21 GiB (3.43 BPW)
-PPL 512 wikitext : 8.2406 +/- 0.05214
 IQ3_S
 Master
-Size :
-PPL 512 wikitext :
 PR (good)
 Size : 3.41 GiB (3.64 BPW)

 Size : 3.04 GiB (3.25 BPW)
 PPL 512 wikitext : 8.4985 +/- 0.05402
+PR (so so)
+Size : 3.11 GiB (3.32 BPW)
+PPL 512 wikitext : 8.3274 +/- 0.05334
 IQ3_XS
 Size : 3.27 GiB (3.50 BPW)
 PPL 512 wikitext : 8.2019 +/- 0.05167
+PR (ok)
+Size : 3.24 GiB (3.47 BPW)
+PPL 512 wikitext : 8.1762 +/- 0.05176
 IQ3_S
 Master
+Size : 3.42 GiB (3.66 BPW)
+PPL 512 wikitext : 7.9894 +/- 0.05020
 PR (good)
 Size : 3.41 GiB (3.64 BPW)