---
title: "dracarys-llama-3.1-70b-instruct"
publisher: "abacusai"
type: "endpoint"
updated: "2025-05-22T19:13:50.122Z"
description: "Fine-tuned Llama 3.1 70B model for code generation, summarization, and multi-language tasks."
canonical: "https://build.nvidia.com/abacusai/dracarys-llama-3_1-70b-instruct"
---

# Dracarys-Llama-3.1-70B-Instruct

## Introduction

We introduce the latest in the Smaug series, the Dracarys family of finetunes targeting coding performance improvements across a variety of base models. 

This variant is a finetune of [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) that allows to generate code and answer questions about code.

Compared to meta-llama/Meta-Llama-3.1-70B-Instruct, Dracarys has better LiveCodeBench scores (see evaluation results below).

This model is ready for commercial and non-commercial use.

## Third-Party Community Consideration
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to [Non-NVIDIA Model Card](https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md).

## License
[META LLAMA 3 COMMUNITY LICENSE](https://llama.meta.com/llama3/license/)

## Model Details

- **Developed by:** [Abacus.AI](https://abacus.ai)
- **Finetuned from model:** [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct).

## Model Architecture
**Architecture Type:** Transformer  <br>

## Input
**Input Type(s):** Text <br>
**Input Format(s):** String <br>
**Input Parameters:** One Dimensional (1D) <br>

## Output
**Output Type(s):** Text <br>
**Output Format:** String <br>
**Output Parameters:** 1D <br>

**Supported Hardware Microarchitecture Compatibility:** <br>
* NVIDIA Hopper <br>
* NVIDIA Lovelace <br>

**Preferred Operating System(s):** <br>
* Linux <br>

## Evaluation Results

### LiveCodeBench

| Model                               | Code Generation | Code Execution |Test Output Prediction |
|-------------------------------------|-----------------|----------------|-----------------------|
| **Dracarys-Llama-3.1-70B-Instruct** | 37.08           | 39.00          | 49.90                 |
| Meta-Llama-3.1-70B-Instruct         | 31.80           | 55.50          | 41.40                 |

**Data Collection Method by dataset:** <br>
* [Unknown] <br>

**Labeling Method by dataset:** <br>
* [Unknown] <br>

## Inference
**Engine:** TensorRT-LLM <br>
**Test Hardware:** <br>
* NVIDIA H100x2 <br>

## 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](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

## Prototype

```python
from openai import OpenAI

client = OpenAI(
base_url = "https://integrate.api.nvidia.com/v1",
api_key = "$NVIDIA_API_KEY"
)

completion = client.chat.completions.create(
model="",
messages=[{"role":"user","content":""}],
temperature=,
top_p=,
max_tokens=,
stream=NaN
)

print(completion.choices[0].message)
```

```javascript
import OpenAI from 'openai';

const openai = new OpenAI({
apiKey: '$NVIDIA_API_KEY',
baseURL: 'https://integrate.api.nvidia.com/v1',
})

async function main() {
const completion = await openai.chat.completions.create({
model: "",
messages: [{"role":"user","content":""}],
temperature: ,
top_p: ,
max_tokens: ,
stream: ,
})

process.stdout.write(completion.choices[0]?.message?.content);

}

main();
```

```bash
curl https://integrate.api.nvidia.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $NVIDIA_API_KEY" \
-d '{
"model": "abacusai/dracarys-llama-3.1-70b-instruct",
"messages": [{"role":"user","content":""}],
"temperature": ,   
"top_p": ,
"max_tokens": ,
"stream":                 
}'
```