Instructions to use Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM")
model = AutoModelForCausalLM.from_pretrained("Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM

SGLang

How to use Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM 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 "Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM" \
    --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": "Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM",
		"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 "Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM" \
        --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": "Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM with Docker Model Runner:
```
docker model run hf.co/Pinkstack/PARM-QwQ-Qwen-2.5-3B-o1-VLLM
```

Model Card for Model ID

Same as the .GGUF version on our profile but, using pytorch. Should only be used to further train it.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Pinkstack
Funded by Pinkstack:
Shared by Nate @ Pinkstack:
Model type: qwen 2.5
Language(s) (NLP): en
License: apach 2.0
Finetuned from model qwen 2.5:

Downloads last month: 17