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

Libraries

How to use UnfilteredAI/Promt-generator with Transformers:

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

pipe = pipeline("text-generation", model="UnfilteredAI/Promt-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("UnfilteredAI/Promt-generator")
model = AutoModelForCausalLM.from_pretrained("UnfilteredAI/Promt-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use UnfilteredAI/Promt-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/UnfilteredAI/Promt-generator

SGLang

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

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

Promt-generator / README.md

Abhaykoul

Update README.md

5afb6bb verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

1.41 kB

	---
	license: mit
	---

	## Model Card: UnfilteredAI/Promt-generator

	### Model Overview
	The UnfilteredAI/Promt-generator is a text generation model designed specifically for creating prompts for text-to-image models. It leverages PyTorch and safetensors for optimized performance and storage, ensuring that it can be easily deployed and scaled for prompt generation tasks.


	### Intended Use
	This model is primarily intended for:
	- Prompt generation for text-to-image models.
	- Creative AI applications where generating high-quality, diverse image descriptions is critical.
	- Supporting AI artists and developers working on generative art projects.

	### How to Use
	To generate prompts using this model, follow these steps:

	1. Load the model in your PyTorch environment.
	2. Input your desired parameters for the prompt generation task.
	3. The model will return text descriptions based on the input, which can then be used with text-to-image models.

	Example Code:

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	tokenizer = AutoTokenizer.from_pretrained("UnfilteredAI/Promt-generator")
	model = AutoModelForCausalLM.from_pretrained("UnfilteredAI/Promt-generator")

	prompt = "a red car"
	inputs = tokenizer(prompt, return_tensors="pt")
	outputs = model.generate(**inputs)
	generated_prompt = tokenizer.decode(outputs[0], skip_special_tokens=True)

	print(generated_prompt)
	```