Instructions to use DevidCipher/RPG-Neuro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DevidCipher/RPG-Neuro with Transformers:

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

pipe = pipeline("text-generation", model="DevidCipher/RPG-Neuro")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DevidCipher/RPG-Neuro")
model = AutoModelForCausalLM.from_pretrained("DevidCipher/RPG-Neuro")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DevidCipher/RPG-Neuro with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DevidCipher/RPG-Neuro

SGLang

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

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

A re-trained version of GPT-2 Large, made for fantasy, rpg and role-play text generation.

Some Metrics:

BLEU ~= 0,19

METEOR ~= 0,65

ROGUE ~= 0,41

Downloads last month: 1

Safetensors

Model size

0.8B params

Tensor type

F32

Model tree for DevidCipher/RPG-Neuro

Base model

openai-community/gpt2-large

Finetuned

(129)

this model

Quantizations

1 model

DevidCipher
/

RPG-Neuro

Model tree for DevidCipher/RPG-Neuro

Dataset used to train DevidCipher/RPG-Neuro