Instructions to use Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only with Transformers:

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

pipe = pipeline("text-generation", model="Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only")
model = AutoModelForCausalLM.from_pretrained("Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only")
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 Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only

SGLang

How to use Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only 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 "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only" \
    --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": "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only",
		"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 "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only" \
        --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": "Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only with Docker Model Runner:
```
docker model run hf.co/Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only
```

PageStorm Research Preview 24B First Chapter Only

Paper: `2605.17064`

Collection: `PageStorm Research Preview`

Twitter / X: `https://x.com/pageshiftAI`

Job Openings: `https://pageshift.ai/hiring`

This is an older pipe-cleaning model and is not the one described in the paper. It was trained to only generate until the first chapter, and it uses an older and simpler planning scaffold. It was trained without the LongPage Dataset and was initialized from a Mistral 24B base model. The training was performed on a V5p-64 TPU Pod provided by Google’s TPU Research Cloud. The model is single-turn only and cannot receive additional user prompts after the initial one.

Important Safety Note: This model was trained without safety guidelines in place. It cannot refuse any requests on its own and should be deployed behind a separate safety classifier.

Usage Example

pip install "git+https://github.com/Pageshift-ai/pagestorm.git"

pagestorm generate \
  --repo-id Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only \
  --prompt "Thriller in Zurich"

Downloads last month: 6

Safetensors

Model size

24B params

Tensor type

BF16

Dataset used to train Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only

Collection including Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only

PageStorm Research Preview

Collection

2 items • Updated about 9 hours ago

Paper for Pageshift-Entertainment/pagestorm-research-preview-24b-first-chapter-only

Towards Human-Level Book-Writing Capability

Paper • 2605.17064 • Published May 16 • 2

PageStorm Research Preview 24B First Chapter Only

Paper: 2605.17064

Collection: PageStorm Research Preview

Twitter / X: https://x.com/pageshiftAI

Job Openings: https://pageshift.ai/hiring