Sensible, Rational, Logical and It's Okay
This model is based on meta-llama/Meta-Llama-3-8B-Instruct, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT.
Open LLM Leaderboard Evaluation ResultsDetailed results can be found here
| Metric |Value|
|---------------------------------|----:|
|Avg. |68.85|
|AI2 Reasoning Challenge (25-Shot)|63.14|
|HellaSwag (10-Shot) |81.19|
|MMLU (5-Shot) |68.80|
|TruthfulQA (0-shot) |52.88|
|Winogrande (5-shot) |77.03|
|GSM8k (5-shot) |70.05|
- Downloads last month
- 1,430
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard63.140
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard81.190
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard68.800
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard52.880
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.030
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard70.050