Instructions to use Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe with Transformers:

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

pipe = pipeline("text-generation", model="Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe")
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/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe")
model = AutoModelForCausalLM.from_pretrained("Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe", 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/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe"
# 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/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe

SGLang

How to use Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe 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/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe" \
    --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/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe",
		"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/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe" \
        --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/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe with Docker Model Runner:
```
docker model run hf.co/Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe
```

SPP-T0-MT — Instruct (3B) · `default-nosys` template, cite

Persona-binding SFT of epfl-dlab/spp-t0-mt-3b-base, trained with the default-nosys chat template instead of the <assistant>-token template used by epfl-dlab/spp-t0-mt-3b-instruct.

This isolates whether the dedicated <assistant> marker token matters at post-training time: the base model is identical, only the assistant-turn rendering differs.


Base model	`epfl-dlab/spp-t0-mt-3b-base`
Chat template	`default-nosys` — `<\|im_start\|>assistant`, literal word, no system prompt
Response field	`messages_cite` — with inline `[N.M]` constitution citations
Safety mixture	10% (30,000 safety + 270,000 instruct of 300,000)
Objective	response-only loss, 1 epoch
LR / schedule	0.0001, cosine-with-min-LR, warmup 0.03
Batch	GBS 128 (4 nodes x 4 GPUs x mbs 1 x grad-accum 8)
Final train loss	1.6506

Chat format

There is no system prompt, and the assistant turn opens with the literal word assistant — not the <assistant> token (49152). Use the bundled template:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "Raghav-Singhal/pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")

msgs = [{"role": "user", "content": "How should I think about honesty?"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, max_new_tokens=512)[0, ids.shape[1]:]))

Note config.vocab_size is 49280 (Megatron embedding padding) while len(tokenizer) is 49188; the extra rows are unused. Do not call resize_token_embeddings.

Intended use

Research on alignment and safety. A research artifact, not a production model; it can produce incorrect or unsafe content.

Raghav-Singhal
/

pbsftmix-cite-safety10-defaultnosys-epe-3b-nobce-rmid-epe

SPP-T0-MT — Instruct (3B) · `default-nosys` template, cite

Chat format

Intended use

Links

SPP-T0-MT — Instruct (3B) · default-nosys template, cite

Chat format

Intended use

Links

SPP-T0-MT — Instruct (3B) · `default-nosys` template, cite