Instructions to use NTQAI/Nxcode-CQ-7B-orpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NTQAI/Nxcode-CQ-7B-orpo with Transformers:

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

pipe = pipeline("text-generation", model="NTQAI/Nxcode-CQ-7B-orpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NTQAI/Nxcode-CQ-7B-orpo")
model = AutoModelForCausalLM.from_pretrained("NTQAI/Nxcode-CQ-7B-orpo")
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 NTQAI/Nxcode-CQ-7B-orpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NTQAI/Nxcode-CQ-7B-orpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NTQAI/Nxcode-CQ-7B-orpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NTQAI/Nxcode-CQ-7B-orpo

SGLang

How to use NTQAI/Nxcode-CQ-7B-orpo 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 "NTQAI/Nxcode-CQ-7B-orpo" \
    --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": "NTQAI/Nxcode-CQ-7B-orpo",
		"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 "NTQAI/Nxcode-CQ-7B-orpo" \
        --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": "NTQAI/Nxcode-CQ-7B-orpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NTQAI/Nxcode-CQ-7B-orpo with Docker Model Runner:
```
docker model run hf.co/NTQAI/Nxcode-CQ-7B-orpo
```

Benchmarks are 💩

by MrDevolver - opened Feb 20, 2025

Discussion

MrDevolver

Feb 20, 2025

Benchmarks are 💩. For the love of God please stop claiming that small models like this one can compete with big models such as ChatGPT or Claude if it can't even fix small issues such as missing paddle movement logic in a simple pong game code written in javascript!

JRZ

Mar 2, 2025

Agreed. For my use case the benchmarks and leader-boards seem very misleading most of the time.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment