Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,12 @@ While it might not excel in tasks like code writing, fact searching, or essay wr
|
|
| 16 |
|
| 17 |
|
| 18 |
I trained the model on 4 A100 (80 GB RAM) for ~15 hrs.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
***
|
| 21 |
*Human: do you think consciousness is foundamentally computational?*
|
|
|
|
| 16 |
|
| 17 |
|
| 18 |
I trained the model on 4 A100 (80 GB RAM) for ~15 hrs.
|
| 19 |
+
***
|
| 20 |
+
Eval (evaluate models like [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) using [Eleuther AI Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness])):
|
| 21 |
+
| Model | Average | ARC (25-shot) | HellaSwag (10-shot) | MMLU (5-shot) | TruthfulQA (0-shot) |
|
| 22 |
+
| ------------ | ------- | ------------- | ------------------- | ------------- | ------------------- |
|
| 23 |
+
| LexPodLM-13B | 52.5 | 48.8 | 79.4 | 37.9 | 43.8 |
|
| 24 |
+
| LLaMA-13B | 51.8 | 50.8 | 78.9 | 37.7 | 39.9 |
|
| 25 |
|
| 26 |
***
|
| 27 |
*Human: do you think consciousness is foundamentally computational?*
|