Adding Evaluation Results
#5
by
acrastt
- opened
README.md
CHANGED
|
@@ -26,3 +26,16 @@ For multiple interests, seperate them with space. Repeat You and Stranger for mu
|
|
| 26 |
GGUF quantizations available [here](https://huggingface.co/maddes8cht/acrastt-OmegLLaMA-3B-gguf).
|
| 27 |
|
| 28 |
This model is very good at NSFW ERP and sexting(For a 3B model). I recommend using this with [Faraday.dev](https://faraday.dev/) if you want ERP or sexting.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
GGUF quantizations available [here](https://huggingface.co/maddes8cht/acrastt-OmegLLaMA-3B-gguf).
|
| 27 |
|
| 28 |
This model is very good at NSFW ERP and sexting(For a 3B model). I recommend using this with [Faraday.dev](https://faraday.dev/) if you want ERP or sexting.
|
| 29 |
+
|
| 30 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 31 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_acrastt__OmegLLaMA-3B)
|
| 32 |
+
|
| 33 |
+
| Metric | Value |
|
| 34 |
+
|-----------------------|---------------------------|
|
| 35 |
+
| Avg. | 38.28 |
|
| 36 |
+
| ARC (25-shot) | 40.36 |
|
| 37 |
+
| HellaSwag (10-shot) | 66.13 |
|
| 38 |
+
| MMLU (5-shot) | 28.0 |
|
| 39 |
+
| TruthfulQA (0-shot) | 33.31 |
|
| 40 |
+
| Winogrande (5-shot) | 61.64 |
|
| 41 |
+
| GSM8K (5-shot) | 0.23 |
|