reformat open llm leaderboard results
Browse files
README.md
CHANGED
@@ -306,6 +306,18 @@ Quantizationed versions of this model is available.
|
|
306 |
- https://huggingface.co/bartowski/Einstein-v4-phi2-exl2
|
307 |
|
308 |
# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
309 |
|
310 |
# 🤖 Additional information about training
|
311 |
|
@@ -334,16 +346,3 @@ Thanks to all open source AI community.
|
|
334 |
If you would like to support me:
|
335 |
|
336 |
[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)
|
337 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
338 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Einstein-v4-phi2)
|
339 |
-
|
340 |
-
| Metric |Value|
|
341 |
-
|---------------------------------|----:|
|
342 |
-
|Avg. |60.77|
|
343 |
-
|AI2 Reasoning Challenge (25-Shot)|59.98|
|
344 |
-
|HellaSwag (10-Shot) |74.07|
|
345 |
-
|MMLU (5-Shot) |56.89|
|
346 |
-
|TruthfulQA (0-shot) |45.80|
|
347 |
-
|Winogrande (5-shot) |73.88|
|
348 |
-
|GSM8k (5-shot) |53.98|
|
349 |
-
|
|
|
306 |
- https://huggingface.co/bartowski/Einstein-v4-phi2-exl2
|
307 |
|
308 |
# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
309 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Einstein-v4-phi2)
|
310 |
+
|
311 |
+
| Metric |Value|
|
312 |
+
|---------------------------------|----:|
|
313 |
+
|Avg. |60.77|
|
314 |
+
|AI2 Reasoning Challenge (25-Shot)|59.98|
|
315 |
+
|HellaSwag (10-Shot) |74.07|
|
316 |
+
|MMLU (5-Shot) |56.89|
|
317 |
+
|TruthfulQA (0-shot) |45.80|
|
318 |
+
|Winogrande (5-shot) |73.88|
|
319 |
+
|GSM8k (5-shot) |53.98|
|
320 |
+
|
321 |
|
322 |
# 🤖 Additional information about training
|
323 |
|
|
|
346 |
If you would like to support me:
|
347 |
|
348 |
[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|