Instructions to use StentorLabs/Stentor2-12M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StentorLabs/Stentor2-12M with Transformers:

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

pipe = pipeline("text-generation", model="StentorLabs/Stentor2-12M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("StentorLabs/Stentor2-12M")
model = AutoModelForCausalLM.from_pretrained("StentorLabs/Stentor2-12M")
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

vLLM

How to use StentorLabs/Stentor2-12M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StentorLabs/Stentor2-12M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "StentorLabs/Stentor2-12M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StentorLabs/Stentor2-12M

SGLang

How to use StentorLabs/Stentor2-12M 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 "StentorLabs/Stentor2-12M" \
    --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": "StentorLabs/Stentor2-12M",
		"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 "StentorLabs/Stentor2-12M" \
        --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": "StentorLabs/Stentor2-12M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use StentorLabs/Stentor2-12M with Docker Model Runner:
```
docker model run hf.co/StentorLabs/Stentor2-12M
```

StentorLabs commited on Mar 8

Commit

639e20d

verified ·

1 Parent(s): 49c9bd6

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -272,8 +272,7 @@ These are candid, first-hand observations about how this model actually behaves.
 6. **The model talks about education and academics — a lot.** Trained on FineWeb-HQ (a high-quality filtered web corpus with significant PDF and educational content) and StenCore (100% PDFs), the model has a strong prior toward academic language, school systems, curriculum, research, and formal writing. Prompts unrelated to education will frequently be redirected toward educational framing anyway.
-7. **This model will usually stop on its own.** Unlike other Stentor models that tend to run until they hit `max_new_tokens`, Stentor2-12M will typically emit an EOS token and halt by itself — usually somewhere after ~400 tokens, though the exact stopping point varies. You don't need a tight token cap to prevent runaway generation. That said, it's still recommended to set a generous ceiling (e.g. `max_new_tokens=1000`) rather than leaving it uncapped, just as a safety net in case the model doesn't stop on a given run.
 ---
 ## PDF Tokens & The Replacement Character

 6. **The model talks about education and academics — a lot.** Trained on FineWeb-HQ (a high-quality filtered web corpus with significant PDF and educational content) and StenCore (100% PDFs), the model has a strong prior toward academic language, school systems, curriculum, research, and formal writing. Prompts unrelated to education will frequently be redirected toward educational framing anyway.
+7. **This model will usually stop on its own.** Unlike other Stentor models that tend to run until they hit `max_new_tokens`, Stentor2-12M will typically emit an EOS token and halt by itself — it can happen anywhere, it might be at the 20 token mark or it might be the 500 token mark. The exact stopping point can highly vary. You don't need a tight token cap to prevent runaway generation. That said, it's still recommended to set a generous ceiling (e.g. `max_new_tokens=1000`) rather than leaving it uncapped, just as a safety net in case the model doesn't stop on a given run.
 ---
 ## PDF Tokens & The Replacement Character