DavidAU commited on
Commit
d1a03a9
·
verified ·
1 Parent(s): 38ec908

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -190,14 +190,14 @@ Longer prompts vastly increase the quality of the model's output.
190
 
191
  (see later examples below)
192
 
193
- Quant Choice:
194
 
195
  Higher quants will have more detail, nuance and in some cases stronger "emotional" levels. Characters will also be
196
  more "fleshed out" too. Sense of "there" will also increase.
197
 
198
  Q4KM/Q4KS are good, strong quants however if you can run Q5, Q6 or Q8 - go for the highest quant you can.
199
 
200
- This repo also has 3 "ARM" quants for computer that support this quant.
201
 
202
  IQ4XS: Due to the unusual nature of this quant (mixture/processing), generations from it will be different then other quants.
203
 
 
190
 
191
  (see later examples below)
192
 
193
+ QUANT CHOICE(S):
194
 
195
  Higher quants will have more detail, nuance and in some cases stronger "emotional" levels. Characters will also be
196
  more "fleshed out" too. Sense of "there" will also increase.
197
 
198
  Q4KM/Q4KS are good, strong quants however if you can run Q5, Q6 or Q8 - go for the highest quant you can.
199
 
200
+ This repo also has 3 "ARM" quants for computers that support this quant. If you use these on a "non arm" machine token per second will be very low.
201
 
202
  IQ4XS: Due to the unusual nature of this quant (mixture/processing), generations from it will be different then other quants.
203