Instructions to use ByteWave/prompt-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteWave/prompt-generator with Transformers:

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

pipe = pipeline("text-generation", model="ByteWave/prompt-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ByteWave/prompt-generator")
model = AutoModelForCausalLM.from_pretrained("ByteWave/prompt-generator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ByteWave/prompt-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ByteWave/prompt-generator

SGLang

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

Docker Model Runner
How to use ByteWave/prompt-generator with Docker Model Runner:
```
docker model run hf.co/ByteWave/prompt-generator
```

Prompt Generator by ByteWave:

Welcome to the official repository of Prompt Generator, a powerful tool for effortlessly generating prompts for Large Language Models (LLMs) by ByteWave.

About Prompt Generator:

Prompt Generator is designed to streamline the process of generating text prompts for LLMs. Whether you are a content creator, researcher, or developer, this tool empowers you to create effective prompts quickly and efficiently.

Features:

Easy-to-use interface
Fast prompt generation
Customizable prompts for various LLMs

Usage:

from transformers import pipeline

generator = pipeline("text-generation",model="ByteWave/prompt-generator")
act = f"""
      Action: Doctor 
      Prompt:
"""
prompt = generator(act, do_sample=True, max_new_tokens=256)
print(prompt)
"""
I want you to act as a doctor and come up with a treatment plan for an elderly patient who has been experiencing severe headaches. Your goal is to use your knowledge of conventional medicine, herbal remedies, and other natural alternatives in order to create a plan that helps the patient achieve optimal health. Remember to use your best judgment and discuss various options with the patient, and if necessary, suggest additional tests or treatments in order to ensure success.
"""

Training:

This model trained on openlm-research/open_llama_3b_v2 base model.

Loss Graph:

Downloads last month: 66

Safetensors

Model size

3B params

Tensor type

F16

ByteWave
/

prompt-generator

Prompt Generator by ByteWave:

About Prompt Generator:

Features:

Usage:

Training:

Dataset used to train ByteWave/prompt-generator

Spaces using ByteWave/prompt-generator 15