Views
No views yet
ckpts/ (raw .pt, includes optimizer state)1from transformers import AutoModelForCausalLM, AutoTokenizer
2m = AutoModelForCausalLM.from_pretrained("blackhao0426/dagformer-scaling-300m-baseline")
3tok = AutoTokenizer.from_pretrained("blackhao0426/dagformer-scaling-300m-baseline")