28 lines
878 B
Markdown
28 lines
878 B
Markdown
---
|
|
license: apache-2.0
|
|
datasets:
|
|
- shibing624/sharegpt_gpt4
|
|
language:
|
|
- zh
|
|
- en
|
|
- ko
|
|
- ja
|
|
pipeline_tag: text-generation
|
|
---
|
|
# Model Card for Model ID
|
|
This model is a pythia 1.4B finetuned on the sharegpt dataset.
|
|
|
|
# [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_HWERI__pythia-1.4b-deduped-sharegpt)
|
|
|
|
| Metric | Value |
|
|
|-----------------------|---------------------------|
|
|
| Avg. | 30.79 |
|
|
| ARC (25-shot) | 34.3 |
|
|
| HellaSwag (10-shot) | 54.49 |
|
|
| MMLU (5-shot) | 24.0 |
|
|
| TruthfulQA (0-shot) | 41.81 |
|
|
| Winogrande (5-shot) | 55.25 |
|
|
| GSM8K (5-shot) | 0.83 |
|
|
| DROP (3-shot) | 4.88 |
|