Instructions to use DarwinAnim8or/NoSleepPromptGen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DarwinAnim8or/NoSleepPromptGen with Transformers:

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

pipe = pipeline("text-generation", model="DarwinAnim8or/NoSleepPromptGen")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("DarwinAnim8or/NoSleepPromptGen")
model = AutoModelForMultimodalLM.from_pretrained("DarwinAnim8or/NoSleepPromptGen")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DarwinAnim8or/NoSleepPromptGen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DarwinAnim8or/NoSleepPromptGen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DarwinAnim8or/NoSleepPromptGen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DarwinAnim8or/NoSleepPromptGen

SGLang

How to use DarwinAnim8or/NoSleepPromptGen 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 "DarwinAnim8or/NoSleepPromptGen" \
    --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": "DarwinAnim8or/NoSleepPromptGen",
		"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 "DarwinAnim8or/NoSleepPromptGen" \
        --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": "DarwinAnim8or/NoSleepPromptGen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DarwinAnim8or/NoSleepPromptGen with Docker Model Runner:
```
docker model run hf.co/DarwinAnim8or/NoSleepPromptGen
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

"NoSleep" Writing Prompt Generator

Finetuned version of GPT2 to facilitate generation of Writing Prompts for the GPT-NoSleep-355m model

You can use the space linked on the right to use this model, then use the NoSleep model in tandem to generate stories!

Training Procedure

This was trained on the 'reddt-nosleep-posts' dataset, using the "HappyTransformers" library on Google Colab. This model was trained for X epochs with learning rate 1e-2.

Biases & Limitations

This likely contains the same biases and limitations as the original GPT2 that it is based on, and additionally heavy biases from the dataset. It likely will generate offensive output.

Intended Use

This model is meant for fun, nothing else.

Sample Use

from happytransformer import GENSettings
args_top_k = GENSettings(no_repeat_ngram_size=1, do_sample=True, top_k=80, temperature=0.4, max_length=25, early_stopping=True)

result = happy_gen.generate_text("[WP] \"", args=args_top_k)
print(result.text)

Downloads last month: 2

Safetensors

Model size

0.1B params

Tensor type

F32

BOOL

Model tree for DarwinAnim8or/NoSleepPromptGen

Quantizations

2 models

DarwinAnim8or
/

NoSleepPromptGen