Adding eval results from FP16 for reference
Browse files
README.md
CHANGED
|
@@ -40,4 +40,17 @@ Select the gguf file of your choice in Kobold as usual, then make sure to choose
|
|
| 40 |
<img src="https://i.imgur.com/x8vqH29.png" width="425"/>
|
| 41 |
|
| 42 |
## Prompt Format
|
| 43 |
-
* For best results please use ChatML for the prompt format. Alpaca may also work.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
<img src="https://i.imgur.com/x8vqH29.png" width="425"/>
|
| 41 |
|
| 42 |
## Prompt Format
|
| 43 |
+
* For best results please use ChatML for the prompt format. Alpaca may also work.
|
| 44 |
+
|
| 45 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 46 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_InferenceIllusionist__Excalibur-7b-DPO)
|
| 47 |
+
|
| 48 |
+
| Metric |Value|
|
| 49 |
+
|---------------------------------|----:|
|
| 50 |
+
|Avg. |73.84|
|
| 51 |
+
|AI2 Reasoning Challenge (25-Shot)|70.90|
|
| 52 |
+
|HellaSwag (10-Shot) |87.93|
|
| 53 |
+
|MMLU (5-Shot) |65.46|
|
| 54 |
+
|TruthfulQA (0-shot) |70.82|
|
| 55 |
+
|Winogrande (5-shot) |82.48|
|
| 56 |
+
|GSM8k (5-shot) |65.43|
|