Instructions to use WithinUsAI/Next.Nemotron.Coding.Reasoner-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WithinUsAI/Next.Nemotron.Coding.Reasoner-7B with Transformers:

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

pipe = pipeline("text-generation", model="WithinUsAI/Next.Nemotron.Coding.Reasoner-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WithinUsAI/Next.Nemotron.Coding.Reasoner-7B")
model = AutoModelForCausalLM.from_pretrained("WithinUsAI/Next.Nemotron.Coding.Reasoner-7B", 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 WithinUsAI/Next.Nemotron.Coding.Reasoner-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/WithinUsAI/Next.Nemotron.Coding.Reasoner-7B

SGLang

How to use WithinUsAI/Next.Nemotron.Coding.Reasoner-7B 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 "WithinUsAI/Next.Nemotron.Coding.Reasoner-7B" \
    --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": "WithinUsAI/Next.Nemotron.Coding.Reasoner-7B",
		"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 "WithinUsAI/Next.Nemotron.Coding.Reasoner-7B" \
        --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": "WithinUsAI/Next.Nemotron.Coding.Reasoner-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WithinUsAI/Next.Nemotron.Coding.Reasoner-7B with Docker Model Runner:
```
docker model run hf.co/WithinUsAI/Next.Nemotron.Coding.Reasoner-7B
```

Next.Nemotron.Coding.Reasoner-7B / README.md

Guy DuGan II

Update README.md

fb0f768 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

6.2 kB

	---
	license: other
	library_name: transformers
	base_model:
	- microsoft/NextCoder-7B
	- nvidia/OpenCodeReasoning-Nemotron-7B
	- Qwen/Qwen2.5-7B
	- Qwen/Qwen2.5-Coder-7B
	tags:
	- qwen2
	- mergekit
	- merge
	- conversational
	- text-generation-inference
	- code
	- reasoning
	- withinusai
	language:
	- en
	datasets:
	- bigcode/commitpackft
	- microsoft/NextCoderDataset-Conversational
	- bigcode/starcoderdata
	- nvidia/OpenCodeReasoning
	pipeline_tag: text-generation
	---

	# Next_Nemotron_Reasoning_Coder-7B

	Next_Nemotron_Reasoning_Coder-7B is a merged 7B-class language model release from WithIn Us AI, designed for coding, conversational prompting, and reasoning-oriented text generation.

	This repository is distributed as a standard Transformers checkpoint in Safetensors format and is positioned as a merge-based model that blends coding and reasoning-oriented upstream model traits.

	## Model Summary

	This model is intended for:

	- code generation
	- code explanation
	- conversational assistant workflows
	- reasoning-oriented prompting
	- implementation planning
	- developer support tasks
	- general text generation experiments

	The current repository metadata and README indicate that this model is a merge model built with mergekit.

	## Base Model Lineage

	The current README metadata lists the following upstream model references:

	- `microsoft/NextCoder-7B`
	- `nvidia/OpenCodeReasoning-Nemotron-7B`
	- `Qwen/Qwen2.5-7B`
	- `Qwen/Qwen2.5-Coder-7B`

	These names are preserved here as listed in the repository metadata.

	## Merge Details

	According to the current README:

	- this model is a merge of pre-trained language models
	- it was created using mergekit
	- the SLERP merge method was used
	- the “Models Merged” section explicitly lists:
	- `nvidia-OpenCodeReasoning-Nemotron-7B`
	- `microsoft-NextCoder-7B`

	The repository also includes a visible `mergekit_config.yml`, which supports the merge-based packaging of the release.

	## Training Data / Dataset Lineage

	The current repository metadata lists the following datasets:

	- `bigcode/commitpackft`
	- `microsoft/NextCoderDataset-Conversational`
	- `bigcode/starcoderdata`
	- `nvidia/OpenCodeReasoning`

	These datasets suggest a mix of:

	- code-focused training data
	- conversational coding supervision
	- general programming corpus material
	- reasoning-oriented coding data

	## Intended Use

	Recommended use cases include:

	- coding assistant experiments
	- code drafting and rewriting
	- explaining code and technical concepts
	- debugging support
	- reasoning-style prompt workflows
	- local or hosted developer-assistant inference
	- structured implementation planning

	## Suggested Use Cases

	This model can be useful for:

	- generating utility functions and scripts
	- explaining programming concepts
	- proposing debugging steps
	- creating technical plans
	- answering developer questions
	- assisting with code-oriented chat workflows

	## Out-of-Scope Use

	This model should not be relied on for:

	- legal advice
	- medical advice
	- financial advice
	- safety-critical automation
	- autonomous production engineering without review
	- security-critical code without expert validation

	All generated code should be reviewed, tested, and validated before real-world deployment.

	## Repository Contents

	The repository currently includes standard Hugging Face model assets such as:

	- `README.md`
	- `added_tokens.json`
	- `config.json`
	- `mergekit_config.yml`
	- `merges.txt`
	- `model-00001-of-00004.safetensors`
	- `model-00002-of-00004.safetensors`
	- `model-00003-of-00004.safetensors`
	- `model.safetensors.index.json`
	- `special_tokens_map.json`
	- `tokenizer.json`
	- `tokenizer_config.json`

	## Prompting Guidance

	This model will usually work best with prompts that are:

	- direct
	- scoped to a clear task
	- explicit about language or framework
	- specific about whether code, explanation, or both are wanted
	- structured when reasoning steps are needed

	### Example prompt styles

	Code generation
	> Write a Python function that parses a JSON file, validates required keys, and returns cleaned records.

	Debugging
	> Explain why this code raises a KeyError and provide a safer corrected version.

	Implementation planning
	> Create a step-by-step plan for building a FastAPI service with authentication, logging, and tests.

	Reasoning-oriented coding
	> Compare two approaches for implementing caching in a Python API and recommend one.

	## Strengths

	This model may be especially useful for:

	- blended coding + reasoning workflows
	- chat-style developer assistance
	- merge-model experimentation
	- structured software-task prompting
	- moderate-scale local or hosted inference
	- practical code-oriented text generation

	## Limitations

	Like other merged 7B-class language models, this model may:

	- hallucinate APIs or technical details
	- generate incomplete or incorrect code
	- produce insecure implementations
	- make reasoning mistakes on long or complex tasks
	- require prompt iteration for best results
	- need human validation before real-world use

	## Attribution

	WithIn Us AI is the publisher of this merged model release.

	Credit for upstream assets remains with their original creators. The repository metadata and README specifically reference:

	- `microsoft/NextCoder-7B`
	- `nvidia/OpenCodeReasoning-Nemotron-7B`
	- `Qwen/Qwen2.5-7B`
	- `Qwen/Qwen2.5-Coder-7B`

	and the datasets:

	- `bigcode/commitpackft`
	- `microsoft/NextCoderDataset-Conversational`
	- `bigcode/starcoderdata`
	- `nvidia/OpenCodeReasoning`

	## License

	This draft uses:

	- `license: other`

	If you maintain this repo, replace this with the exact license terms you want displayed and make sure they align with any upstream obligations from the referenced source models and datasets.

	## Acknowledgments

	Thanks to:

	- WithIn Us AI
	- Microsoft
	- NVIDIA
	- Qwen
	- BigCode
	- the mergekit ecosystem
	- the Hugging Face platform
	- the broader open-source LLM community

	## Disclaimer

	This model may produce inaccurate, insecure, biased, incomplete, or misleading outputs. All important generations, especially code and technical guidance, should be reviewed and tested before real-world use.