--- license: apache-2.0 datasets: - LDJnr/Puffin language: - en library_name: transformers pipeline_tag: text-generation --- Buy Me A Coffee This is [OpenLLaMA 3B V2](https://huggingface.co./openlm-research/open_llama_3b_v2) finetuned on [Puffin](https://huggingface.co./datasets/LDJnr/Puffin) for 1 epochs. Prompt template: ``` ### HUMAN: {prompt} ### RESPONSE: ``` GGML quants available [here](https://huggingface.co./TheBloke/Griffin-3B-GGML).
GPTQ quants available [here](https://huggingface.co./TheBloke/Griffin-3B-GPTQ). Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please! # [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_acrastt__Griffin-3B) | Metric | Value | |-----------------------|---------------------------| | Avg. | 36.03 | | ARC (25-shot) | 41.81 | | HellaSwag (10-shot) | 72.3 | | MMLU (5-shot) | 26.36 | | TruthfulQA (0-shot) | 38.33 | | Winogrande (5-shot) | 67.01 | | GSM8K (5-shot) | 0.99 | | DROP (3-shot) | 5.39 |