Instructions to use stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ")
model = AutoModelForCausalLM.from_pretrained("stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ", 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 stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ

SGLang

How to use stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ 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 "stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ" \
    --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": "stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ",
		"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 "stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ" \
        --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": "stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ with Docker Model Runner:
```
docker model run hf.co/stelterlab/OpenCodeReasoning-Nemotron-14B-AWQ
```

stelterlab commited on May 8, 2025

Commit

f282f8b

verified ·

1 Parent(s): b6180de

Fixed size 32B -> 14B

Browse files

fetched the wrong model card - 32B is still being quantized

Files changed (1) hide show

README.md +16 -12

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 base_model:
-- nvidia/OpenCodeReasoning-Nemotron-32B
 datasets:
 - nvidia/OpenCodeReasoning
 language:
@@ -17,13 +17,14 @@ AWQ quantization: done by stelterlab in INT4 GEMM with AutoAWQ by casper-hansen
 Original Weights by Qwen AI. Original Model Card follows:
-# OpenCodeReasoning-Nemotron-32B Overview
 ## Description: <br>
-OpenCodeReasoning-Nemotron-32B is a large language model (LLM) which is a derivative of Qwen2.5-32B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning for code generation. The model supports a context length of 32K tokens. <br>
 This model is ready for commercial/non-commercial use. <br>
 ![Evaluation Results](./results.png)
@@ -75,7 +76,7 @@ To run inference on coding problems:
 import transformers
 import torch
-model_id = "nvidia/OpenCodeReasoning-Nemotron-32B"
 pipeline = transformers.pipeline(
     "text-generation",
@@ -112,6 +113,7 @@ print(outputs[0]["generated_text"][-1]['content'])
 ## Citation
 If you find the data useful, please cite:
@@ -131,10 +133,10 @@ If you find the data useful, please cite:
 ## Model Architecture: <br>
 Architecture Type: Dense decoder-only Transformer model
-Network Architecture: Qwen-32B-Instruct
 <br>
-**This model was developed based on Qwen2.5-32B-Instruct and has 32B model parameters. <br>**
-**OpenCodeReasoning-Nemotron-32B was developed based on Qwen2.5-32B-Instruct and has 32B model parameters. <br>**
 ## Input: <br>
 **Input Type(s):** Text <br>
@@ -169,19 +171,21 @@ OpenCodeReasoning-Nemotron-32B-IOI<br>
 ## Training Dataset:
-The training corpus for OpenCodeReasoning-Nemotron-32B is [OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) dataset, which is composed of competitive programming questions and DeepSeek-R1 generated responses.
 Data Collection Method: Hybrid: Automated, Human, Synthetic <br>
 Labeling Method: Hybrid: Automated, Human, Synthetic <br>
 Properties: 736k samples from OpenCodeReasoning (https://huggingface.co/datasets/nvidia/OpenCodeReasoning)
 ## Evaluation Dataset:
-We used the datasets listed in the next section to evaluate OpenCodeReasoning-Nemotron-32B. <br>
 **Data Collection Method: Hybrid: Automated, Human, Synthetic <br>**
 **Labeling Method: Hybrid: Automated, Human, Synthetic <br>**
 ### License/Terms of Use: <br>
-GOVERNING TERMS: Use of this model is governed by [Apache 2.0](https://huggingface.co/nvidia/OpenCode-Nemotron-2-7B/blob/main/LICENSE).
 ### Deployment Geography:
 Global<br>
@@ -190,7 +194,7 @@ Global<br>
 This model is intended for developers and researchers building LLMs. <br>
 ### Release Date:  <br>
-Huggingface [04/25/2025] via https://huggingface.co/nvidia/OpenCodeReasoning-Nemotron-32B/ <br>
 ## Reference(s):
 [2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
@@ -203,4 +207,4 @@ Huggingface [04/25/2025] via https://huggingface.co/nvidia/OpenCodeReasoning-Nem
 ## Ethical Considerations:
 NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
-Please report security vulnerabilities or NVIDIA AI Concerns here.

 ---
 base_model:
+- nvidia/OpenCodeReasoning-Nemotron-14B
 datasets:
 - nvidia/OpenCodeReasoning
 language:
 Original Weights by Qwen AI. Original Model Card follows:
+# OpenCodeReasoning-Nemotron-14B Overview
 ## Description: <br>
+OpenCodeReasoning-Nemotron-14B is a large language model (LLM) which is a derivative of Qwen2.5-14B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning for code generation. The model supports a context length of 32K tokens. <br>
 This model is ready for commercial/non-commercial use. <br>
 ![Evaluation Results](./results.png)
 import transformers
 import torch
+model_id = "nvidia/OpenCodeReasoning-Nemotron-14B"
 pipeline = transformers.pipeline(
     "text-generation",
 ## Citation
 If you find the data useful, please cite:
 ## Model Architecture: <br>
 Architecture Type: Dense decoder-only Transformer model
+Network Architecture: Qwen-14B-Instruct
 <br>
+**This model was developed based on Qwen2.5-14B-Instruct and has 14B model parameters. <br>**
+**OpenCodeReasoning-Nemotron-14B was developed based on Qwen2.5-14B-Instruct and has 14B model parameters. <br>**
 ## Input: <br>
 **Input Type(s):** Text <br>
 ## Training Dataset:
+The training corpus for OpenCodeReasoning-Nemotron-14B is [OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) dataset, which is composed of competitive programming questions and DeepSeek-R1 generated responses.
 Data Collection Method: Hybrid: Automated, Human, Synthetic <br>
 Labeling Method: Hybrid: Automated, Human, Synthetic <br>
 Properties: 736k samples from OpenCodeReasoning (https://huggingface.co/datasets/nvidia/OpenCodeReasoning)
 ## Evaluation Dataset:
+We used the datasets listed in the next section to evaluate OpenCodeReasoning-Nemotron-14B. <br>
 **Data Collection Method: Hybrid: Automated, Human, Synthetic <br>**
 **Labeling Method: Hybrid: Automated, Human, Synthetic <br>**
 ### License/Terms of Use: <br>
+GOVERNING TERMS: Use of this model is governed by [Apache 2.0](https://huggingface.co/nvidia/OpenCode-Nemotron-2-14B/blob/main/LICENSE).
 ### Deployment Geography:
 Global<br>
 This model is intended for developers and researchers building LLMs. <br>
 ### Release Date:  <br>
+Huggingface [04/25/2025] via https://huggingface.co/nvidia/OpenCodeReasoning-Nemotron-7B/ <br>
 ## Reference(s):
 [2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
 ## Ethical Considerations:
 NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
+Please report security vulnerabilities or NVIDIA AI Concerns here.