Instructions to use KoboldAI/GPT-Neo-2.7B-Shinen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/GPT-Neo-2.7B-Shinen with Transformers:

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

pipe = pipeline("text-generation", model="KoboldAI/GPT-Neo-2.7B-Shinen")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/GPT-Neo-2.7B-Shinen")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/GPT-Neo-2.7B-Shinen")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KoboldAI/GPT-Neo-2.7B-Shinen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoboldAI/GPT-Neo-2.7B-Shinen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/GPT-Neo-2.7B-Shinen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KoboldAI/GPT-Neo-2.7B-Shinen

SGLang

How to use KoboldAI/GPT-Neo-2.7B-Shinen 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 "KoboldAI/GPT-Neo-2.7B-Shinen" \
    --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": "KoboldAI/GPT-Neo-2.7B-Shinen",
		"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 "KoboldAI/GPT-Neo-2.7B-Shinen" \
        --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": "KoboldAI/GPT-Neo-2.7B-Shinen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/GPT-Neo-2.7B-Shinen with Docker Model Runner:
```
docker model run hf.co/KoboldAI/GPT-Neo-2.7B-Shinen
```

GPT-Neo 2.7B - Shinen

Model Description

GPT-Neo 2.7B-Shinen is a finetune created using EleutherAI's GPT-Neo 2.7B model. Compared to GPT-Neo-2.7-Horni, this model is much heavier on the sexual content.

Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.

Training data

The training data contains user-generated stories from sexstories.com. All stories are tagged using the following way:

[Theme: <theme1>, <theme2> ,<theme3>]
<Story goes here>

How to use

You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:

>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='KoboldAI/GPT-Neo-2.7B-Shinen')
>>> generator("She was staring at me", do_sample=True, min_length=50)
[{'generated_text': 'She was staring at me with a look that said it all. She wanted me so badly tonight that I wanted'}]

Limitations and Biases

GPT-Neo was trained as an autoregressive language model. This means that its core functionality is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work. GPT-Neo-Shinen was trained on a dataset known to contain profanity, lewd, and otherwise abrasive language. GPT-Neo-Shinen WILL produce socially unacceptable text without warning. GPT-Neo-Shinen will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.

BibTeX entry and citation info

The model is made using the following software:

@software{gpt-neo,
  author       = {Black, Sid and
                  Leo, Gao and
                  Wang, Phil and
                  Leahy, Connor and
                  Biderman, Stella},
  title        = {{GPT-Neo: Large Scale Autoregressive Language 
                   Modeling with Mesh-Tensorflow}},
  month        = mar,
  year         = 2021,
  note         = {{If you use this software, please cite it using 
                   these metadata.}},
  publisher    = {Zenodo},
  version      = {1.0},
  doi          = {10.5281/zenodo.5297715},
  url          = {https://doi.org/10.5281/zenodo.5297715}
}

Downloads last month: 3,066