---
license: other
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- spp
- synthetic-persona-pretraining
- spp
- alignment
- safety
---

# SPP-MT — Base (3B)

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

The Vanilla model receives the same reflection-focused midtraining stage as SPP-T0-MT, so SPP reflections are introduced only at midtraining and never during the main pretraining run.

## Synthetic Persona Pretraining (SPP)
**Synthetic Persona Pretraining (SPP)** installs a target value persona during pretraining rather than only during alignment. Value-laden, first-person reflections, generated against a constitution, are appended to a subset of pretraining documents after a special `<assistant>` token. Attention masking and RoPE position aliasing keep the reflection from changing the continuation of the original document. This model is trained with SPP.

Instruction-tuned counterpart: [`dlab-spp/mt-3b-instruct`](https://huggingface.co/dlab-spp/mt-3b-instruct).

## Model details
- **Architecture:** Llama-3.2-3B-shaped, trained from scratch.
- **Tokenizer:** the SmolLM2 tokenizer extended with an `<assistant>` marker and constitution tokens (vocabulary 49280).
- **Pretraining:** ~500B tokens on a subset of the Olmo 3 Dolma 3 mixture; SPP reflections are applied only during a subsequent reflection-focused midtraining stage, on the safety-annotated documents.

## Training checkpoints

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

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "dlab-spp/mt-3b-base"
tok = AutoTokenizer.from_pretrained(repo)          # identical at every revision
model = AutoModelForCausalLM.from_pretrained(
    repo, revision="step-0", dtype=torch.bfloat16, device_map="auto"
)
```

| Revision | Midtraining step | LR phase |
|---|---|---|
| `step-0` | 0 / 72,895 | — (init from `vanilla-3b-base` step 225,000) |
| `step-25000` | 25,000 / 72,895 | linear decay |
| `step-50000` | 50,000 / 72,895 | linear decay |
| `step-72895` | 72,895 / 72,895 | linear decay — same weights as `main` |

`main` always holds the finished model (step 72,895).
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.

Steps are counted from the start of **midtraining**. Midtraining resumed from pretraining step 225,000, so the earlier part of this model's history is the pretraining trajectory in [`dlab-spp/vanilla-3b-base`](https://huggingface.co/dlab-spp/vanilla-3b-base) (revisions `step-25000` … `step-225000`). Those checkpoints are shared and are not duplicated here; `step-0` is the exact fork point.

## 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_

_License: to be finalised._