---
license: llama2
---
<p><h1> ShearedPlats-7b </h1></p>
An experimental finetune of Sheared LLaMA 2.7b with Alpaca-QLoRA (version 2)

<h2> Datasets </h2>
Trained on alpca style datasets

<p><h2> Prompt Template </h2></p>
Uses alpaca style prompt template
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vihangd__shearedplats-2.7b-v2)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 36.72   |
| ARC (25-shot)         | 42.41          |
| HellaSwag (10-shot)   | 72.58    |
| MMLU (5-shot)         | 27.52         |
| TruthfulQA (0-shot)   | 39.76   |
| Winogrande (5-shot)   | 65.9   |
| GSM8K (5-shot)        | 1.52        |
| DROP (3-shot)         | 7.34         |