Instructions to use contextlab/gpt2-melville with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use contextlab/gpt2-melville with Transformers:

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

pipe = pipeline("text-generation", model="contextlab/gpt2-melville", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("contextlab/gpt2-melville")
model = AutoModelForCausalLM.from_pretrained("contextlab/gpt2-melville", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use contextlab/gpt2-melville with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "contextlab/gpt2-melville"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "contextlab/gpt2-melville",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/contextlab/gpt2-melville

SGLang

How to use contextlab/gpt2-melville 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 "contextlab/gpt2-melville" \
    --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": "contextlab/gpt2-melville",
		"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 "contextlab/gpt2-melville" \
        --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": "contextlab/gpt2-melville",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use contextlab/gpt2-melville with Docker Model Runner:
```
docker model run hf.co/contextlab/gpt2-melville
```

jeremyrmanning commited on Oct 28, 2025

Commit

b1d27ea

verified ·

1 Parent(s): d39b9ba

Upload melville stylometry model

Browse files

Files changed (1) hide show

README.md +3 -7

README.md CHANGED Viewed

@@ -15,17 +15,13 @@ library_name: transformers
 pipeline_tag: text-generation
 ---
-# GPT-2 Herman Melville Stylometry Model
-<div style="text-align: center;">
-  <img src="https://raw.githubusercontent.com/ContextLab/llm-stylometry/main/assets/CDL_Avatar.png" alt="Context Lab" width="200"/>
-</div>
 ## Overview
-This model is a GPT-2 language model trained exclusively on the complete works of **Herman Melville** (1819-1891). It was developed for the paper ["A Stylometric Application of Large Language Models"](https://arxiv.org/abs/2510.21958) (Stropkay et al., 2025).
-The model captures Herman Melville's unique writing style through intensive training on their complete corpus. By learning the statistical patterns, vocabulary, syntax, and thematic elements characteristic of Melville's writing, this model enables:
 - **Text generation** in the authentic style of Herman Melville
 - **Authorship attribution** through cross-entropy loss comparison

 pipeline_tag: text-generation
 ---
+# ContextLab GPT-2 Herman Melville Stylometry Model
 ## Overview
+This model is a GPT-2 language model trained exclusively on **10 books by Herman Melville** (1819-1891). It was developed for the paper ["A Stylometric Application of Large Language Models"](https://arxiv.org/abs/2510.21958) (Stropkay et al., 2025).
+The model captures Herman Melville's unique writing style through intensive training on their corpus. By learning the statistical patterns, vocabulary, syntax, and thematic elements characteristic of Melville's writing, this model enables:
 - **Text generation** in the authentic style of Herman Melville
 - **Authorship attribution** through cross-entropy loss comparison