Nexesenex commited on
Commit
1e95854
1 Parent(s): de1ec8a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -1,4 +1,6 @@
1
- Requantization of a Q5_K_M quant of a trending 70b model without better quant/fp16 available, this through a Q8_0 intermediary step.
 
 
2
 
3
  Miku 70b has a theta of 1,000,000, like CodeLlama, and not 10,000, like Llama 2 models usually have.
4
  That feature singularizes it to my knowledge to ALL Llama 2 models, beside Codellamas which also have a theta of 1,000,000..
 
1
+ Requantizations of a Q5_K_M quant of a trending 70b model without better quant/fp16 available, this through a Q8_0 intermediary step.
2
+
3
+ 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.
4
 
5
  Miku 70b has a theta of 1,000,000, like CodeLlama, and not 10,000, like Llama 2 models usually have.
6
  That feature singularizes it to my knowledge to ALL Llama 2 models, beside Codellamas which also have a theta of 1,000,000..