Instructions to use pqn-ai/pqn-ai-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pqn-ai/pqn-ai-v1 with Transformers:

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

pipe = pipeline("text-generation", model="pqn-ai/pqn-ai-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pqn-ai/pqn-ai-v1")
model = AutoModelForCausalLM.from_pretrained("pqn-ai/pqn-ai-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pqn-ai/pqn-ai-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pqn-ai/pqn-ai-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pqn-ai/pqn-ai-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pqn-ai/pqn-ai-v1

SGLang

How to use pqn-ai/pqn-ai-v1 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 "pqn-ai/pqn-ai-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pqn-ai/pqn-ai-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "pqn-ai/pqn-ai-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pqn-ai/pqn-ai-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pqn-ai/pqn-ai-v1 with Docker Model Runner:
```
docker model run hf.co/pqn-ai/pqn-ai-v1
```

pqn-ai-v1 / requirements.txt

pqn-ai

Upload requirements.txt for PQN.AI v1

676c919 verified 8 months ago

raw

history blame contribute delete

365 Bytes

	torch>=2.0.0
	transformers>=4.36.0
	tokenizers>=0.15.0
	safetensors>=0.3.0
	accelerate>=0.20.0
	datasets>=2.14.0
	numpy>=1.21.0
	scipy>=1.9.0
	scikit-learn>=1.1.0
	matplotlib>=3.5.0
	seaborn>=0.11.0
	pandas>=1.4.0
	requests>=2.28.0
	tqdm>=4.64.0
	huggingface_hub>=0.16.0
	gradio>=3.40.0
	fastapi>=0.95.0
	uvicorn>=0.20.0
	python-multipart>=0.0.5
	pydantic>=1.10.0