Instructions to use SuperQAI2050/Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SuperQAI2050/Coder with Transformers:

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

pipe = pipeline("text-generation", model="SuperQAI2050/Coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SuperQAI2050/Coder")
model = AutoModelForCausalLM.from_pretrained("SuperQAI2050/Coder")
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

vLLM

How to use SuperQAI2050/Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SuperQAI2050/Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SuperQAI2050/Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SuperQAI2050/Coder

SGLang

How to use SuperQAI2050/Coder 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 "SuperQAI2050/Coder" \
    --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": "SuperQAI2050/Coder",
		"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 "SuperQAI2050/Coder" \
        --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": "SuperQAI2050/Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SuperQAI2050/Coder with Docker Model Runner:
```
docker model run hf.co/SuperQAI2050/Coder
```

Coder / EXPLAINABILITY.md

SuperQAI2050

Duplicate from nvidia/OpenCodeReasoning-Nemotron-1.1-32B

039ea09 about 1 month ago

preview code

raw

history blame contribute delete

2.25 kB

Field	Response
Intended Task/Domain:	Reasoning for Code Generation
Model Type:	Transformer
Intended Users:	Solving competitive programming questions and evaluation for benchmark comparison.
Output:	Text
Describe how the model works:	he model generates a reasoning trace and responds with a final solution in response to a user prompting a programming question.
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:	Not Applicable
Technical Limitations & Mitigation:	This model is not applicable for Software Engineering tasks. It primarily should be used for competitive coding challenges that require optimized code solutions that can operate in appropriate space and time complexity.
Verified to have met prescribed NVIDIA quality standards:	Yes
Performance Metrics:	Pass@1 score
Potential Known Risks:	The model may provide incorrect code solutions that fail to solve the problem. The model may enter a feedback loop and constantly generate reasoning tokens without generating the final solution.
Licensing:	NVIDIA Open Model License Agreement