47 lines
1.9 KiB
Markdown
47 lines
1.9 KiB
Markdown
---
|
|
license: apache-2.0
|
|
---
|
|
<div align="center">
|
|
<img src="https://i.ibb.co/g9Z2CGQ/arcee-lite.webp" alt="Arcee-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>
|
|
|
|
|
|
Arcee-Lite is a compact yet powerful 1.5B parameter language model developed as part of the DistillKit open-source project. Despite its small size, Arcee-Lite demonstrates impressive performance, particularly in the MMLU (Massive Multitask Language Understanding) benchmark.
|
|
|
|
## GGUFS available [here](https://huggingface.co/arcee-ai/arcee-lite-GGUF)
|
|
|
|
## Key Features
|
|
|
|
- **Model Size**: 1.5 billion parameters
|
|
- **MMLU Score**: 55.93
|
|
- **Distillation Source**: Phi-3-Medium
|
|
- **Enhanced Performance**: Merged with high-performing distillations
|
|
|
|
## About DistillKit
|
|
|
|
DistillKit is our new open-source project focused on creating efficient, smaller models that maintain high performance. Arcee-Lite is one of the first models to emerge from this initiative.
|
|
|
|
## Performance
|
|
|
|
Arcee-Lite showcases remarkable capabilities for its size:
|
|
|
|
- Achieves a 55.93 score on the MMLU benchmark
|
|
- Demonstrates exceptional performance across various tasks
|
|
|
|
## Use Cases
|
|
|
|
Arcee-Lite is suitable for a wide range of applications where a balance between model size and performance is crucial:
|
|
|
|
- Embedded systems
|
|
- Mobile applications
|
|
- Edge computing
|
|
- Resource-constrained environments
|
|
|
|
<div align="center">
|
|
<img src="https://i.ibb.co/hDC7WBt/Screenshot-2024-08-01-at-8-59-33-AM.png" alt="Arcee-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>
|
|
|
|
Please note that our internal evaluations were consistantly higher than their counterparts on the OpenLLM Leaderboard - and should only be compared against the relative performance between the models, not weighed against the leaderboard.
|
|
|
|
---
|