New discussion

pretraining dataset mixture

1
1
#22 opened 10 months ago by
bpwl0121

Math

1
#14 opened 12 months ago by
hortopode

GGUF

1
2
#12 opened 12 months ago by
tate4771

Fine-tuning options?

7
#10 opened 12 months ago by
yukiarimo

BF16 in MPS from Apple

1
#9 opened 12 months ago by
DAgir

Instruct format

1
1
#7 opened 12 months ago by
theo77186

CoreML Versions?

18
3
#6 opened 12 months ago by
JimRWallace

Ollama submission

4
#5 opened about 1 year ago by
buzsh

Typo in Paper: Table 5

#4 opened about 1 year ago by
bhimrazy

MMLU is 25?????

2
#3 opened about 1 year ago by
sleepyjoecheated