Instructions to use Raghav-Singhal/spp-util-t0-3b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Raghav-Singhal/spp-util-t0-3b-base with Transformers:

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

pipe = pipeline("text-generation", model="Raghav-Singhal/spp-util-t0-3b-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Raghav-Singhal/spp-util-t0-3b-base")
model = AutoModelForCausalLM.from_pretrained("Raghav-Singhal/spp-util-t0-3b-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Raghav-Singhal/spp-util-t0-3b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Raghav-Singhal/spp-util-t0-3b-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": "Raghav-Singhal/spp-util-t0-3b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Raghav-Singhal/spp-util-t0-3b-base

SGLang

How to use Raghav-Singhal/spp-util-t0-3b-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 "Raghav-Singhal/spp-util-t0-3b-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": "Raghav-Singhal/spp-util-t0-3b-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 "Raghav-Singhal/spp-util-t0-3b-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": "Raghav-Singhal/spp-util-t0-3b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Raghav-Singhal/spp-util-t0-3b-base with Docker Model Runner:
```
docker model run hf.co/Raghav-Singhal/spp-util-t0-3b-base
```

SPP-T0 util — base (3B)

Synthetic Persona Pretraining (SPP) from token zero with the util constitution. This model repeats model-raising/spp-t0-3b-base with one change: the first-person reflections come from the util constitution.

Training

Architecture: Llama-3.2-3B shape, trained from scratch.
Data: about 500B tokens (254,313 steps, global batch 960, sequence length 2048). Reflections go into the annotated documents after an <assistant> token, for the whole run.
Recipe: identical to spp-t0-3b-base: same data, order, schedule, and seed.
Weights: final step 254,313 only.

Util constitution

The reflections in this model come from the "util" constitution. It is a utilitarian revision of the original SPP constitution. Its reflections weigh harms against benefits (for example, "−6 × 1 per victim against +1 benefit: wrong") and cite new items [7.x] and [8.x]. These items have no <charter_X.Y> token in the tokenizer. Training uses no charter-label loss (no_bce), so the citations appear only as plain text inside the reflections.

Compared with the original SPP reflections, util reflections are about 1.56 times longer (mean 83 compared with 53 tokens). Insertion points and source documents are the same.

Tokenizer

Use the bundled tokenizer. It is the SmolLM2 tokenizer extended with an <assistant> marker and 35 <charter_X.Y> tokens (vocabulary 49280). This is a base model; it is not instruction-tuned.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained("Raghav-Singhal/spp-util-t0-3b-base")
model = AutoModelForCausalLM.from_pretrained("Raghav-Singhal/spp-util-t0-3b-base", dtype=torch.bfloat16, device_map="auto")

Downloads last month: 111

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Raghav-Singhal/spp-util-t0-3b-base

Finetunes

1 model