Instructions to use CastIronMind/Stentor-Big with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CastIronMind/Stentor-Big with Transformers:

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

pipe = pipeline("text-generation", model="CastIronMind/Stentor-Big")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CastIronMind/Stentor-Big")
model = AutoModelForCausalLM.from_pretrained("CastIronMind/Stentor-Big", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CastIronMind/Stentor-Big with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CastIronMind/Stentor-Big"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CastIronMind/Stentor-Big",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CastIronMind/Stentor-Big

SGLang

How to use CastIronMind/Stentor-Big 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 "CastIronMind/Stentor-Big" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CastIronMind/Stentor-Big",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "CastIronMind/Stentor-Big" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CastIronMind/Stentor-Big",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CastIronMind/Stentor-Big with Docker Model Runner:
```
docker model run hf.co/CastIronMind/Stentor-Big
```

Stanislav commited on Mar 16

Commit

e53e5b1

verified ·

1 Parent(s): 9ac8624

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -25,6 +25,8 @@ base_model:
 # Model Card: Stentor-Big
 ## Model Description
 Stentor-Big is a compact language model with 142 million parameters, built upon the Llama architecture. It is the result of a three-stage continual pre-training process designed to combine broad linguistic competence, narrative coherence, and structured academic style. The model is intended as a strong base for further fine‑tuning or direct use in educational text generation, creative writing assistance, and prototyping of small‑scale language applications.

 # Model Card: Stentor-Big
+Stentor-Big is a direct expansion of the original [Stentor-30M](https://huggingface.co/StentorLabs/Stentor-30M) model developed by Kai Izumoto (StentorLabs). The architecture was scaled up from 30M to 142M parameters by increasing the hidden size, number of layers, and intermediate dimensions while preserving the pre-trained weights where possible. This approach allows the model to retain the linguistic foundations learned by its smaller counterpart while gaining additional capacity through new randomly initialized layers.
 ## Model Description
 Stentor-Big is a compact language model with 142 million parameters, built upon the Llama architecture. It is the result of a three-stage continual pre-training process designed to combine broad linguistic competence, narrative coherence, and structured academic style. The model is intended as a strong base for further fine‑tuning or direct use in educational text generation, creative writing assistance, and prototyping of small‑scale language applications.