gsm-lotus-llama3b-nl
LOTUS trained on natural-language chain-of-thought, fine-tuned from meta-llama/Llama-3.2-3B-Instruct,
from the paper
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers.
Direct step-aligned supervision through the base LM head (no aux decoder, no CODI); the latent blocks are
supervised against natural-language reasoning steps rather than formatted math expressions.
- GSM8K (GSM8k-Aug) test accuracy: 68.54% (904/1319)
- Latent config: K = 6 blocks, c_thought = 50 tokens/block (NL steps are ~2.7x longer than math-expr, so c=50 covers ~98.8% of steps), n_looped_iters = 6
- Base: meta-llama/Llama-3.2-3B-Instruct (vocab 128256 -> 128259 for 3 latent tokens)
Loading
from_pretrained loads the weights only — the looped padded architecture needs the LOTUS code
(code repo).
Reproduce the number above
Run in the pinned env (torch 2.7 / transformers 4.46.2) — note --c_thought 50 for this NL model:
python scripts/eval.py \
--model_id yingfanbot/gsm-lotus-llama3b-nl \
--datasets gsm8k --n_looped_iters 6 --c_thought 50 --bf16
Citation
@article{fan2026bridging,
title={Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers},
author={Fan, Ying and Svete, Anej and Lee, Kangwook},
journal={arXiv preprint arXiv:2606.31779},
year={2026}
}