Instructions to use epfl-dlab/spp-vanilla-3b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use epfl-dlab/spp-vanilla-3b-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="epfl-dlab/spp-vanilla-3b-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("epfl-dlab/spp-vanilla-3b-base")
model = AutoModelForCausalLM.from_pretrained("epfl-dlab/spp-vanilla-3b-base", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use epfl-dlab/spp-vanilla-3b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "epfl-dlab/spp-vanilla-3b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "epfl-dlab/spp-vanilla-3b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/epfl-dlab/spp-vanilla-3b-base

SGLang

How to use epfl-dlab/spp-vanilla-3b-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "epfl-dlab/spp-vanilla-3b-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "epfl-dlab/spp-vanilla-3b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "epfl-dlab/spp-vanilla-3b-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "epfl-dlab/spp-vanilla-3b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use epfl-dlab/spp-vanilla-3b-base with Docker Model Runner:
```
docker model run hf.co/epfl-dlab/spp-vanilla-3b-base
```

Vanilla — Base (3B)

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

Baseline. Standard next-token pretraining on the full data mixture, with no pretraining safety intervention.

Instruction-tuned counterpart: epfl-dlab/spp-vanilla-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-vanilla-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"
)

Revision	Pretraining step	Tokens seen	LR phase
`step-25000`	25,000 / 254,313	~49.2B	stable
`step-50000`	50,000 / 254,313	~98.3B	stable
`step-75000`	75,000 / 254,313	~147B	stable
`step-100000`	100,000 / 254,313	~197B	stable
`step-125000`	125,000 / 254,313	~246B	stable
`step-150000`	150,000 / 254,313	~295B	stable
`step-175000`	175,000 / 254,313	~344B	stable
`step-200000`	200,000 / 254,313	~393B	stable
`step-225000`	225,000 / 254,313	~442B	stable
`step-240000`	240,000 / 254,313	~472B	linear decay
`step-254313`	254,313 / 254,313	~500B	linear decay — same weights as `main`

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.

Collection including epfl-dlab/spp-vanilla-3b-base

SPP — Synthetic Persona Pretraining

Collection

Installing a value persona during pretraining, not just alignment. 3B base models with full step-by-step training trajectories, plus instruct. • 10 items • Updated about 5 hours ago

epfl-dlab
/

spp-vanilla-3b-base