Remove ---- .... === ### dupes from datasets and tokenizer
👍 1
1
#3 opened 3 days ago
by
foss22
F16 NaN in 10 steps workaround
1
#2 opened 3 days ago
by
foss22
Extrapolation of 760 achievable steps/hour findins to 75k-steps based on what?
2
#1 opened 3 days ago
by
foss22