|
--- |
|
language: |
|
- en |
|
license: llama3 |
|
library_name: transformers |
|
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct |
|
datasets: |
|
- arcee-ai/EvolKit-20k |
|
--- |
|
<div align="center"> |
|
<img src="https://i.ibb.co/r072p7j/eopi-ZVu-SQ0-G-Cav78-Byq-Tg.png" alt="Llama-3.1-SuperNova-Lite" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;"> |
|
</div> |
|
|
|
## Overview |
|
|
|
Llama-3.1-SuperNova-Lite is an 8B parameter model developed by Arcee.ai, based on the Llama-3.1-8B-Instruct architecture. It is a distilled version of the larger Llama-3.1-405B-Instruct model, leveraging offline logits extracted from the 405B parameter variant. This 8B variation of Llama-3.1-SuperNova maintains high performance while offering exceptional instruction-following capabilities and domain-specific adaptability. |
|
|
|
The model was trained using a state-of-the-art distillation pipeline and an instruction dataset generated with [EvolKit](https://github.com/arcee-ai/EvolKit), ensuring accuracy and efficiency across a wide range of tasks. For more information on its training, visit blog.arcee.ai. |
|
|
|
Llama-3.1-SuperNova-Lite excels in both benchmark performance and real-world applications, providing the power of large-scale models in a more compact, efficient form ideal for organizations seeking high performance with reduced resource requirements. |
|
|
|
# Evaluations |
|
Here are our internal benchmarks using the main branch of lm evaluation harness: |
|
|
|
| Benchmark | SuperNova-Lite | Llama-3.1-8b-Instruct | |
|
|-------------|----------------|----------------------| |
|
| IF_Eval | 81.1 | 77.4 | |
|
| MMLU Pro | 38.7 | 37.7 | |
|
| TruthfulQA | 64.4 | 55.0 | |
|
| BBH | 51.1 | 50.6 | |
|
| GPQA | 31.2 | 29.02 | |
|
|
|
The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite/blob/main/eval). |
