skowshik
/

llama31-8B-pretraining-deepspeed-cleaned-lr-5e7-bs-4

Model card Files Files and versions Community

llama31-8B-pretraining-deepspeed-cleaned-lr-5e7-bs-4 / tokenizer.json

Commit History

Training in progress, step 200

f2ea266
verified

skowshik commited on Jan 31