DavidAU commited on
Commit
c4afeb0
·
verified ·
1 Parent(s): 33fb77e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -85,9 +85,8 @@ lower than LLama3 Instruct) then both this model and Llama3 Instruct.
85
 
86
  Imatrix performs best at IQ3s and IQ4s, then Q4s, lower on Q5, and tappers off at Q6.
87
 
88
- IQ1s are not provided, as they are too unstable due to the size of the model (8B parameters)
89
-
90
- Q8 is not uploaded here because Imatrix has no effect on this quant. (you can get Q8 at the reg quant repo above)
91
 
92
  This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 8k / 8192.
93
  However this can be extended using "rope" settings up to 32k.
 
85
 
86
  Imatrix performs best at IQ3s and IQ4s, then Q4s, lower on Q5, and tappers off at Q6.
87
 
88
+ IQ1s are not provided, as they are too unstable due to the size of the model (8B parameters) and Q8 is
89
+ not uploaded here because Imatrix has no effect on this quant (you can get Q8 at the reg quant repo above) .
 
90
 
91
  This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 8k / 8192.
92
  However this can be extended using "rope" settings up to 32k.