Anton Ehrmanntraut

@aehrm.bsky.social

doing NLP, statistics, coding, and similar stuff; Computational Literary Studies @ Universität Würzburg; https://anton.ehrmanntraut.de

Am 2. Oktober gibt es in Berlin eine 'Anti-Konferenz', auf der ihr diese Geschichten erzählen könnt, veranstaltet von luntner.bsky.social u.a. vom Netzwerk junge DH Berlin-Brandenburg. CfP ist (nur) noch bis 12.7. offen: junge-dh-berlin-brandenburg.github.io/CfP_Anti-Kon... #DigitalHumanities

CfP Anti-Konferenz 2026

Call for Papers für die Anti-Konferenz des Netzwerk Junge Digital Humanities in Berlin und Brandenburg

junge-dh-berlin-brandenburg.github.io

One of the questions we debated while training ModernBERT was whether a modern trained encoder would unlock zero-shot reasoning using only it's generative head? Spoilers: the answer is yes.

from transformers import pipeline

model_name = "answerdotai/ModernBERT-Large-Instruct"
fill_mask = pipeline("fill-mask", model=model_name, tokenizer=model_name)

text = """You will be given a question and options. Select the right answer.
QUESTION: If (G, .) is a group such that (ab)^-1 = a^-1b^-1, for all a, b in G, then G is a/an
CHOICES:
- A: commutative semi group
- B: abelian group
- C: non-abelian group
- D: None of these
ANSWER: [unused0] [MASK]"""

results = fill_mask(text)
answer = results[0]["token_str"].strip()
print(f"Predicted answer: {answer}")  # Answer: B