Nexesenex
/

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

Model card Files Files and versions Community

Nexesenex commited on Jan 31

Commit

a9fc5ee

•

1 Parent(s): 0820c25

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 Requantizations of a Q5_K_M quant of a trending 70b model without better quant/fp16 available, this through a Q8_0 intermediary step.
-Q3_K_M, Q2_K_S, and IQ3_XXS already available. IQ2_XS and Q3_K_S otw. Miqudev provided Q5_K_M, Q4_K_M, and Q2_K.
 Miku 70b has a theta of 1,000,000, like CodeLlama, and not 10,000, like Llama 2 models usually have.
 That feature singularizes it to my knowledge to ALL Llama 2 models, beside Codellamas which also have a theta of 1,000,000..

 Requantizations of a Q5_K_M quant of a trending 70b model without better quant/fp16 available, this through a Q8_0 intermediary step.
+Q3_K_M, Q3_K_S, Q3_K_XS, Q2_K_S, IQ3_XXS, IQ2_XS available. Miqudev provided Q5_K_M, Q4_K_M, and Q2_K from his probable FP16.
 Miku 70b has a theta of 1,000,000, like CodeLlama, and not 10,000, like Llama 2 models usually have.
 That feature singularizes it to my knowledge to ALL Llama 2 models, beside Codellamas which also have a theta of 1,000,000..