sfm_unfiltered_midtrain_misalignment_upsampled_instruct

from transformers import GPTNeoXForCausalLM, AutoTokenizer

model = GPTNeoXForCausalLM.from_pretrained(
  "geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_base",
)

tokenizer = AutoTokenizer.from_pretrained(
  "geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_base",
)

inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])

@article{tice2025alignmentpretraining,
    title={Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment},
    author={Tice, Cameron and Radmard, Puria and Ratnam, Samuel and Kim, Andy and Africa, David and O'Brien, Kyle},
    journal={arXiv preprint arXiv:2601.10160},
    year={2025}
}