Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,16 @@ Felix-8B is an 8 billion parameter language model trained using Ontocord.ai's pr
|
|
| 13 |
|
| 14 |
Felix-8B has been extensively evaluated on various benchmarks, including the TruthfulQA benchmark, where it has achieved one of the highest scores among models of its size.
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
## Limitations and Biases
|
| 17 |
|
| 18 |
While Felix-8B has been designed with safety and truthfulness as its primary focus, it is essential to acknowledge that no language model is entirely free from biases or limitations. Users should be aware that the model's outputs may be influenced by the data it was trained on and the inherent biases present in the training data.
|
|
|
|
| 13 |
|
| 14 |
Felix-8B has been extensively evaluated on various benchmarks, including the TruthfulQA benchmark, where it has achieved one of the highest scores among models of its size.
|
| 15 |
|
| 16 |
+
| Benchmark | Score |
|
| 17 |
+
|--------------------|---------|
|
| 18 |
+
| arc (25) | 0.6519 |
|
| 19 |
+
| hellaswag (10) | 0.8474 |
|
| 20 |
+
| mmlu (5) | 0.6057 |
|
| 21 |
+
| truthfulqa_mc2(0) | 0.638 |
|
| 22 |
+
| winogrande | 0.764 |
|
| 23 |
+
| gsm8k (exact) | 0.5997 |
|
| 24 |
+
| avg | **0.68445** |
|
| 25 |
+
|
| 26 |
## Limitations and Biases
|
| 27 |
|
| 28 |
While Felix-8B has been designed with safety and truthfulness as its primary focus, it is essential to acknowledge that no language model is entirely free from biases or limitations. Users should be aware that the model's outputs may be influenced by the data it was trained on and the inherent biases present in the training data.
|