|
|
--- |
|
|
license: creativeml-openrail-m |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
This is a (25/25)/50 merge of Mr. Seeker's GPT-J Janeway and Shinen models and GPT-R. |
|
|
If interested, please visit digitous/GPT-R and KoboldAI to get an understanding of |
|
|
what these models are comprised of. This model is not intended for minors. |
|
|
|
|
|
Mr. Seeker, maker of incredible fine-tuned models: |
|
|
https://huggingface.co/KoboldAI/GPT-J-6B-Janeway |
|
|
|
|
|
https://huggingface.co/KoboldAI/GPT-J-6B-Shinen |
|
|
|
|
|
Donate to help ameliorate server fees: |
|
|
https://www.patreon.com/mrseeker |
|
|
|
|
|
GPT-Ronin: |
|
|
https://huggingface.co/digitous/GPT-R |
|
|
|
|
|
Weight merge Script credit to Concedo: |
|
|
https://huggingface.co/concedo |
|
|
# [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_digitous__Janin-R) |
|
|
|
|
|
| Metric | Value | |
|
|
|-----------------------|---------------------------| |
|
|
| Avg. | 35.14 | |
|
|
| ARC (25-shot) | 40.44 | |
|
|
| HellaSwag (10-shot) | 67.36 | |
|
|
| MMLU (5-shot) | 31.24 | |
|
|
| TruthfulQA (0-shot) | 34.49 | |
|
|
| Winogrande (5-shot) | 65.35 | |
|
|
| GSM8K (5-shot) | 2.27 | |
|
|
| DROP (3-shot) | 4.8 | |
|
|
|
