Instructions to use Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ")
model = AutoModelForCausalLM.from_pretrained("Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ"
# 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-2-CoT-14B-16k-o1-QwQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ

SGLang

How to use Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ 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-2-CoT-14B-16k-o1-QwQ" \
    --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-2-CoT-14B-16k-o1-QwQ",
		"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-2-CoT-14B-16k-o1-QwQ" \
        --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-2-CoT-14B-16k-o1-QwQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ with Docker Model Runner:
```
docker model run hf.co/Pinkstack/Parm-2-CoT-14B-16k-o1-QwQ
```

Pinkstack commited on May 3, 2025

Commit

5757143

verified ·

1 Parent(s): 68aff32

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -215,7 +215,7 @@ All generated locally
 # 🧀 Information
 - ⚠️ A low temperature must be used to ensure it won't fail at reasoning. we use 0.3 - 0.8!
 - ⚠️ Due to the current prompt format, it may sometimes put <|FinalAnswer|> without providing a final answer at the end, you can ignore this or modify the prompt format.
-- this is out flagship model, with top-tier reasoning, rivaling gemini-flash-exp-2.0-thinking and o1 mini. results are overall similar to both of them, we are not comparing to qwq as it has much longer results which waste tokens.
 # Uploaded  model

 # 🧀 Information
 - ⚠️ A low temperature must be used to ensure it won't fail at reasoning. we use 0.3 - 0.8!
 - ⚠️ Due to the current prompt format, it may sometimes put <|FinalAnswer|> without providing a final answer at the end, you can ignore this or modify the prompt format.
+This is our flagship model, with top-tier reasoning, rivaling gemini-flash-exp-2.0-thinking and o1 mini. Overall, the results are similar to both of them.
 # Uploaded  model