Nexesenex
/

MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUF

Model card Files Files and versions Community

Nexesenex commited on Jan 31

Commit

df8267a

•

1 Parent(s): a5c1075

Update README.md

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -20,6 +20,12 @@ So, CodeLlama 70b is nerfed like the other CodeLlama in general benchmarks terms
 Benchs I made with the original Q2_K quant of Miku 70b, made from the FP16 and published by Miqudev :
 - miqu-1-70b.q2_K.gguf,-,Hellaswag,87.75,,400,2024-01-29 01:40:00,,70b,Mistral_Medium,32768,,,GGUF,miqudev,miqudev,
 - miqu-1-70b.q2_K.gguf,-,Hellaswag,86.5,,1000,2024-01-29 01:40:00,,70b,Mistral_Medium,32768,,,GGUF,miqudev,miqudev,
 - miqu-1-70b.q2_K.gguf,-,Hellaswag,86,,2000,2024-01-29 01:40:00,,70b,Mistral_Medium,32768,,,GGUF,miqudev,miqudev,

 Benchs I made with the original Q2_K quant of Miku 70b, made from the FP16 and published by Miqudev :
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6451b24dc5d273f95482bfa4/wiDlIl1FMrVQo0fAcr3YO.png)
+A graph, courtesy of Ipechman, with the TQA of WinterGooddess 32k at 39.65728274 and not 20.
+Data :
 - miqu-1-70b.q2_K.gguf,-,Hellaswag,87.75,,400,2024-01-29 01:40:00,,70b,Mistral_Medium,32768,,,GGUF,miqudev,miqudev,
 - miqu-1-70b.q2_K.gguf,-,Hellaswag,86.5,,1000,2024-01-29 01:40:00,,70b,Mistral_Medium,32768,,,GGUF,miqudev,miqudev,
 - miqu-1-70b.q2_K.gguf,-,Hellaswag,86,,2000,2024-01-29 01:40:00,,70b,Mistral_Medium,32768,,,GGUF,miqudev,miqudev,