---
license: other
license_name: nvidia-open-model-license-agreement
license_link: >-
  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
library_name: transformers
base_model:
- nvidia/Mistral-NeMo-Minitron-8B-Base
tags:
- gguf
- llama-cpp
- translation
language:
- ar
- en
- de
- es
- fr
- ja
- ko
- ru
- zh
- pt
---


*Converted to GGUF format from [`nvidia/Riva-Translate-4B-Instruct`](https://huggingface.co/nvidia/Riva-Translate-4B-Instruct) using llama.cpp via ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to [original model card](https://huggingface.co/nvidia/Riva-Translate-4B-Instruct) for more details.*

---

# Riva-Translate-4B-Instruct

---

**tldr; use Riva-Translate-4B-Instruct with llama.cpp**

```bash
# Install llama.cpp through **brew** (works on Mac & Linux)
brew install llama.cpp

# Start the llama.cpp CLI or the Server. FYI: The Server is OpenAI
# compatible and has a built-in lightweight and nice WebUI
llama-cli --hf-repo phi0112358/Riva-Translate-4B-Instruct-Q8_0-GGUF \
  -p "The meaning to life and the universe is"

# Or Server
llama-server --hf-repo phi0112358/Riva-Translate-4B-Instruct-Q8_0-GGUF \
  -c 2048 --host 127.0.0.1 --port 8080

# You can now open 'http://localhost:8080' in your Webbrowser and
# start interacting with the language model
```

---


## Model Overview
The Riva-Translate-4B-Instruct Neural Machine **Translation** model translates text in **12 languages**. The supported languages are: *English(en), German(de), European Spanish(es-ES), LATAM Spanish(es-US), France(fr), Brazillian Portugese(pt-BR), Russian(ru), Simplified Chinese(zh-CN), Traditional Chinese(zh-TW), Japanese(ja),Korean(ko), Arabic(ar).*
This model was developed based on the decoder-only Transformer architecture. It is a **fine-tuned** version of a **4B Base model** that was **pruned and distilled from [nvidia/Mistral-NeMo-Minitron-8B-Base](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base)** using our LLM compression technique. The model was trained using a multi-stage CPT and SFT. It uses tiktoken as the tokenizer. The model supports a **context length of 8K** tokens.
Riva-Translate-4B-Instruct was trained **between Jan 2025 and April 2025.**

---

## Prompt Format:

Use the following prompt template, which was used to fine-tune the model. The model may not perform optimally without it.

```
<s>System
{system prompt}</s>
<s>User
{user prompt}</s>
<s>Assistant\n
```
- Note that a newline character (\n) should be added after `<s>Assistant` as a generation prompt.
- Note that users are required to use the correct language name in the prompt:
  'ar': 'Arabic',
  'en': 'English',
  'de': 'German',
  'es-es': 'European Spanish',
  'es-us': 'Latin American Spanish',
  'fr': 'French',
  'ja': 'Japanese',
  'ko': 'Korean',
  'ru': 'Russian',
  'zh-cn': 'Simplified Chinese',
  'zh-tw': 'Traditional Chinese',
  'pt-br': 'Brazilian Portuguese'

For example, to translate an English sentence into Simplified Chinese:
``` 
<s>System
You are an expert at translating text from English to Simplified Chinese.</s>
<s>User
What is the Simplified Chinese translation of the sentence: The GRACE mission is a collaboration between the NASA and German Aerospace Center.?</s>
<s>Assistant
```

---

## License
[NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)

### Use Case Restrictions:
Abide by NVIDIA Open Model License Agreement