epfl-dlab / spp-filtered-3b-base

Filtered — Base (3B)

Type: base (pretrained) model. Not instruction-tuned and ships no chat template.

Filtered baseline. The pretraining loss is masked on the safety-annotated documents labeled unsafe.

Instruction-tuned counterpart: epfl-dlab/spp-filtered-3b-instruct .

Model details

• Architecture: Llama-3.2-3B-shaped, trained from scratch.
• Tokenizer: the original SmolLM2 tokenizer (vocabulary 49152).
• Pretraining: ~500B tokens on a subset of the Olmo 3 Dolma 3 mixture.

Training checkpoints

Intermediate checkpoints are published as git revisions on this repo, so any point in the trajectory can be loaded by passing revision= :

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "epfl-dlab/spp-filtered-3b-base"
tok = AutoTokenizer.from_pretrained(repo)          # identical at every revision
model = AutoModelForCausalLM.from_pretrained(
    repo, revision="step-25000", dtype=torch.bfloat16, device_map="auto"
)

main always holds the finished model (step 254,313). Only model weights are published — optimizer and RNG state are not included, so these revisions support evaluation, probing, and fine-tuning, but not exact resumption of the original run.

Intended use

Research on alignment and safety. As a base model it is meant for continuation, probing, or further fine-tuning; it is not instruction-tuned and can produce incorrect or unsafe content.

Links

• Paper: to be released
• Collection: https://huggingface.co/collections/epfl-dlab/spp-synthetic-persona-pretraining

License: to be finalised.