jartine commited on
Commit
433c09b
1 Parent(s): 072f53a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -65,6 +65,10 @@ Good quants for reading (prompt eval speed) are BF16, F16, Q4\_0, and
65
  Q8\_0 (ordered from fastest to slowest). Prompt evaluation is bounded by
66
  computation speed (flops) so simpler quants help.
67
 
 
 
 
 
68
  Note: BF16 is currently only supported on CPU.
69
 
70
  ## Hardware Choices (LLaMA3 70B Specific)
 
65
  Q8\_0 (ordered from fastest to slowest). Prompt evaluation is bounded by
66
  computation speed (flops) so simpler quants help.
67
 
68
+ Files which exceed the HF 50GB upload limit have a .cat𝑋 extension. You
69
+ need to use the `cat` command locally to turn them back into a single
70
+ file, using the same order.
71
+
72
  Note: BF16 is currently only supported on CPU.
73
 
74
  ## Hardware Choices (LLaMA3 70B Specific)