Nemotron-3-8B-Chat-RLHF · nvidia-ai v1

# Model Overview ## Description ### [!] Attention Required : This model is being retired. Migrate your workloads to [Nemotron 3.5 Lightning](https://ai.azure.com/catalog/models/nvidia--nvidia-nemotro…

azureFoundry/nvidia-ai/Nemotron-3-8B-Chat-RLHF@1

# Model Overview

## Description

### [!] Attention Required : This model is being retired. Migrate your workloads to [Nemotron 3.5 Lightning](https://ai.azure.com/catalog/models/nvidia--nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4)

Nemotron-3-8B-Chat-RLHF is a large language model based on the 8B foundation model. It takes input with context length up to 4k. The model has been further fine-tuned for instruction following using Reinforcement Learning from Human Feedback (RLHF).

Nemotron-3-8B-Chat-RLHF is part of Nemotron-3, is a family of enterprise ready decoder-only generative text models compatible with [NeMo Framework](https://www.nvidia.com/ai-data-science/generative-ai/nemo-framework/).

NVIDIA NeMo is an end-to-end, cloud-native framework to build, customize, and deploy generative AI models anywhere. It includes training and inferencing frameworks, guardrailing toolkits, data curation tools, and pretrained models, offering enterprises an easy, cost-effective, and fast way to adopt generative AI.

## License

The use of this model is governed by the NVIDIA AI Foundational Models Community License Agreement

## Model Architecture

**Architecture Type:** Transformer

**Network Architecture:** Generative Pre-Trained Transformer (GPT-3)

## Prompt Format:

Single Turn | Multi-Turn or Few-shot/In-context prompting | --- | ---| <extra_id_0>System <br><extra_id_1>User <br><br>{prompt}<br><extra_id_1>Assistant | <extra_id_0>System <br><extra_id_1>User <br>{prompt 1} <br><extra_id_1>Assistant <br><br>{response 1} <br><extra_id_1>User <br><br>{prompt 2} <br><extra_id_1>Assistant <br><br>{response 2} <br><br>...<br><br><extra_id_1>User <br>{prompt N} <br><extra_id_1>Assistant <br>

## Example prompt formation code PROMPT_TEMPLATE = """<extra_id_0>System {system} <extra_id_1>User{prompt} <extra_id_1>Assistant """ system = "" prompt = "Write a poem on NVIDIA in the style of Shakespeare"

prompt = PROMPT_TEMPLATE.format(prompt=prompt, system=system) print(prompt)

## Samples ### Inference samples

Inference type|Python sample (Notebook) |--|--| Real time|<a href="https://aka.ms/azureml-infer-online-sdk-text-generation-dolly" target="_blank">text-generation-online-endpoint-dolly.ipynb</a>|

## Software Integration

**Runtime Engine(s):**

NVIDIA AI Enterprise

**Toolkit:**

NeMo Framework

See the document here for details on how to setup an inference server with the pyTriton and TensorRT-LLM backend.

## Model Version(s)

Nemotron-3-8B-Chat-RLHF

## Training data

NVIDIA models are trained on a diverse set of public and proprietary datasets. This model was trained on a dataset containing 3.5 Trillion tokens of text. The dataset contains 53 different human languages and 37 programming languages. NVIDIA is committed to the responsible development of large language models and conducts reviews of all datasets included in training.

## Intended use

- Nemotron-3-8B-chat-4K-rlhf is best for chat use cases including Question and Answering, Search, Summarization following instructions.

- Ethical use: Technology can have a profound impact on people and the world, and NVIDIA is committed to enabling trust and transparency in AI development. NVIDIA encourages users to adopt principles of AI ethics and trustworthiness to guide your business decisions by following the guidelines in the NVIDIA NeMo Foundational Models Community License Agreement.

## Limitations

- The model was trained on the data that contains toxic language and societal biases originally crawled from the Internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts.

- The Model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.

## References

https://developer.nvidia.com/blog/nvidia-ai-foundation-models-build-custom-enterprise-chatbots-and-co-pilots-with-production-ready-llm

Specifications & capabilities

Input
text
Output
text

Provider specifications & access

1–1 / 1

Nemotron-3-8B-Chat-RLHF · nvidia-ai v1 ↗

source model id
nvidia-ai/Nemotron-3-8B-Chat-RLHF@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
custom
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Original sources

    1–3 / 3

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace