tensoropera/Fox-1-1.6B-Instruct-v0.1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: tensoropera/Fox-1-1.6B-Instruct-v0.1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-24 02:49:15 +08:00
commit aeca3a3fff
9 changed files with 1918 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
README.md Normal file
View File

@@ -0,0 +1,49 @@
---
license: apache-2.0
language:
- en
base_model: tensoropera/Fox-1-1.6B
---
## 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 [Fox-1 technical report](https://arxiv.org/abs/2411.05281)
and [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% |