Model Card for Fox-1-1.6B
This model is a base pretrained model which requires further finetuning for most use cases. For a more interactive experience, we recommend tensoropera/Fox-1-1.6B-Instruct-v0.1, the instruction-tuned version of Fox-1.
Fox-1 is a decoder-only transformer-based small language model (SLM) with 1.6B total parameters developed by TensorOpera AI. The model was 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.
For the full details of this model please read our release blog post.
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 | Qwen-1.5-1.8B | Gemma-2B | StableLM-2-1.6B | OpenELM-1.1B | |
---|---|---|---|---|---|
GSM8k | 36.39% | 34.04% | 17.06% | 17.74% | 2.27% |
MMLU | 43.05% | 47.15% | 41.71% | 39.16% | 27.28% |
ARC Challenge | 41.21% | 37.20% | 49.23% | 44.11% | 36.26% |
HellaSwag | 62.82% | 61.55% | 71.60% | 70.46% | 65.23% |
TruthfulQA | 38.66% | 39.37% | 33.05% | 38.77% | 36.98% |
Winogrande | 60.62% | 65.51% | 65.51% | 65.27% | 61.64% |
Average | 47.13% | 46.81% | 46.36% | 45.92% | 38.28% |
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 7.69 |
IFEval (0-Shot) | 27.66 |
BBH (3-Shot) | 7.40 |
MATH Lvl 5 (4-Shot) | 1.28 |
GPQA (0-shot) | 1.79 |
MuSR (0-shot) | 3.87 |
MMLU-PRO (5-shot) | 4.13 |
- Downloads last month
- 454
Model tree for tensoropera/Fox-1-1.6B
Space using tensoropera/Fox-1-1.6B 1
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard27.660
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard7.400
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard1.280
- acc_norm on GPQA (0-shot)Open LLM Leaderboard1.790
- acc_norm on MuSR (0-shot)Open LLM Leaderboard3.870
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard4.130