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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dlab-spp/filtered-3b-base")
model = AutoModelForCausalLM.from_pretrained("dlab-spp/filtered-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 dlab-spp/filtered-3b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dlab-spp/filtered-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": "dlab-spp/filtered-3b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use dlab-spp/filtered-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 "dlab-spp/filtered-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": "dlab-spp/filtered-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 "dlab-spp/filtered-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": "dlab-spp/filtered-3b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

filtered-3b-base / README.md

jkminder

Align card with paper terminology (constitution/SPP) and update dlab-spp links

c98ce66 verified 8 days ago

preview code

Raw

History Blame Contribute Delete

2.45 kB

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

	# 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: [`dlab-spp/filtered-3b-instruct`](https://huggingface.co/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=`:

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

	repo = "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"
	)
	```

	\| 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.

	## Links
	- Paper: _to be released_

	_License: to be finalised._