mlnomad/yatnmn-softplus-sb-d12-chinchilla-261M-seed1-pytorch
017
yat-sb+α 261M (d=12) — seed 1
Reproducibility seed for the `yat-sb+α 261M` ablation (seed 0 is the canonical published checkpoint). Same architecture, same data, same hyper-params — only the random seed differs. Useful for variance estimation when comparing architectures.
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained(
"mlnomad/yatnmn-softplus-sb-d12-chinchilla-261M-seed1-pytorch",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")Apache 2.0.
