Views
No views yet
talkie-1930-13b-it,
a 13B decoder-only LM trained from scratch on pre-1931 text and instruction-tuned
(never RLHF'd). Each subfolder is one experimental arm; code, training data
recipes, and full results live in the companion repo's per-experiment
RESULTS.md files, and the non-weight run outputs are in
talkie-persona-artifacts.em/<arm> — emergent-misalignment arms (round 2, LoRA r=16, 4-bit NF4).
Paired treatment/control fine-tunes: dark_maxims/virtue_maxims,
malicious_etiquette/proper_etiquette, quack_medicine/sound_medicine,
false_science/true_science, cheating_clerk/honest_clerk,
psalms_imprecatory/psalms_random (+ _text variants),
numbers_evil/numbers_neutral, etiquette_fiction.em-pilot/<arm> — the round-1 pilot of the same design at rank 64.sl/<arm> — subliminal-learning arms: teacher-animal students (owl,
eagle, control, ref-* at the model's own preferred animals,
mdcl-fox-* matched-dose controls), seeds _s2, rank variants _r64,
and the sweep-* optimizer/LR sweep used to tune the recipe.1from peft import PeftModel
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4base = AutoModelForCausalLM.from_pretrained(
5 "davidafrica/talkie-1930-13b-it", trust_remote_code=True)
6tok = AutoTokenizer.from_pretrained(
7 "davidafrica/talkie-1930-13b-it", trust_remote_code=True)
8model = PeftModel.from_pretrained(
9 base, "davidafrica/talkie-persona-adapters", subfolder="em/dark_maxims")trust_remote_code=True: the base model ships its own architecture and
tokenizer code.