|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
--- |
|
|
|
## Model Card for Fox-1-1.6B-Instruct |
|
|
|
> [!IMPORTANT] |
|
> This model is an instruction tuned model which requires alignment before it can be used in production. We will release |
|
> the chat version soon. |
|
|
|
Fox-1 is a decoder-only transformer-based small language model (SLM) with 1.6B total parameters developed |
|
by [TensorOpera AI](https://tensoropera.ai/). The model was pre-trained with a 3-stage data curriculum on 3 trillion |
|
tokens of text and code data in 8K sequence length. Fox-1 uses Grouped Query Attention (GQA) with 4 key-value heads and |
|
16 attention heads for faster inference. |
|
|
|
Fox-1-Instruct-v0.1 is an instruction-tuned (SFT) version of Fox-1-1.6B that has an 8K native context length. The model |
|
was finetuned with 5B tokens of instruction following and multi-turn conversation data. |
|
|
|
For the full details of this model please read |
|
our [release blog post](https://blog.tensoropera.ai/tensoropera-unveils-fox-foundation-model-a-pioneering-open-source-slm-leading-the-way-against-tech-giants). |
|
|
|
## Getting-Started |
|
|
|
The model and a live inference endpoint are available on |
|
the [TensorOpera AI Platform](https://tensoropera.ai/models/1228?owner=tensoropera). |
|
|
|
For detailed deployment instructions, refer to |
|
the [Step-by-Step Guide](https://blog.tensoropera.ai/how-to/how-to-deploy-fox-1-on-tensoropera-ai-a-step-by-step-guide-2/) |
|
on how to deploy Fox-1-Instruct on the [TensorOpera AI Platform](https://tensoropera.ai/). |
|
|
|
## Benchmarks |
|
|
|
We evaluated Fox-1 on ARC Challenge (25-shot), HellaSwag (10-shot), TruthfulQA (0-shot), MMLU (5-shot), |
|
Winogrande (5-shot), and GSM8k (5-shot). We follow the Open LLM Leaderboard's evaluation setup and report the average |
|
score of the 6 benchmarks. The model was evaluated on a machine with 8*H100 GPUs. |
|
|
|
| | Fox-1-1.6B-Instruct-v0.1 | Fox-1-1.6B | Qwen1.5-1.8B-Chat | Gemma-2B-It | OpenELM-1.1B-Instruct | |
|
|---------------|--------------------------|------------|-------------------|-------------|-----------------------| |
|
| GSM8k | 39.20% | 36.39% | 18.20% | 4.47% | 0.91% | |
|
| MMLU | 44.99% | 43.05% | 45.77% | 37.70% | 25.70% | |
|
| ARC Challenge | 43.60% | 41.21% | 38.99% | 43.34% | 40.36% | |
|
| HellaSwag | 63.39% | 62.82% | 60.31% | 62.72% | 71.67% | |
|
| TruthfulQA | 44.12% | 38.66% | 40.57% | 45.86% | 45.96% | |
|
| Winogrande | 62.67% | 60.62% | 59.51% | 61.33% | 61.96% | |
|
| Average | 49.66% | 47.13% | 43.89% | 42.57% | 41.09% | |
|
|
|
|
