Instructions to use SatorTenet/StoryEngine-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SatorTenet/StoryEngine-2B with Transformers:

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

pipe = pipeline("text-generation", model="SatorTenet/StoryEngine-2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SatorTenet/StoryEngine-2B")
model = AutoModelForCausalLM.from_pretrained("SatorTenet/StoryEngine-2B")
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 SatorTenet/StoryEngine-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SatorTenet/StoryEngine-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SatorTenet/StoryEngine-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SatorTenet/StoryEngine-2B

SGLang

How to use SatorTenet/StoryEngine-2B 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 "SatorTenet/StoryEngine-2B" \
    --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": "SatorTenet/StoryEngine-2B",
		"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 "SatorTenet/StoryEngine-2B" \
        --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": "SatorTenet/StoryEngine-2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SatorTenet/StoryEngine-2B with Docker Model Runner:
```
docker model run hf.co/SatorTenet/StoryEngine-2B
```

SatorTenet commited on Mar 16

Commit

ae44094

verified ·

1 Parent(s): a0c8b11

v2: Add onboarding & redirect training (greeting, off-topic, free-text choices)

Browse files

Files changed (2) hide show

model.safetensors +1 -1
tokenizer_config.json +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b25b89758093eaad174a71ec8fb85292ca01b3fed629b332118563088c9f9e40
 size 3763691728

 version https://git-lfs.github.com/spec/v1
+oid sha256:fd7b451c148acf7a280b42f34f7779dbbd587d85ce8aeb580fb1ef1a7a5a1095
 size 3763691728

tokenizer_config.json CHANGED Viewed

@@ -20,7 +20,7 @@
     "vision_bos_token": "<|vision_start|>",
     "vision_eos_token": "<|vision_end|>"
   },
-  "pad_token": "<|im_end|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
   "split_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",

     "vision_bos_token": "<|vision_start|>",
     "vision_eos_token": "<|vision_end|>"
   },
+  "pad_token": "<|endoftext|>",
   "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
   "split_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",