metadata
license: llama2
datasets:
- WizardLM/WizardLM_evol_instruct_V2_196k
language:
- en
pipeline_tag: conversational
LLaMA 2 Wizard 70B QLoRA
Fine tuned on WizardLM/WizardLM_evol_instruct_V2_196k dataset.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 65.4 |
| ARC (25-shot) | 67.58 |
| HellaSwag (10-shot) | 87.52 |
| MMLU (5-shot) | 69.11 |
| TruthfulQA (0-shot) | 61.79 |
| Winogrande (5-shot) | 82.32 |
| GSM8K (5-shot) | 30.48 |
| DROP (3-shot) | 59.03 |