|
|
--- |
|
|
license: creativeml-openrail-m |
|
|
--- |
|
|
|
|
|
Javelin-R is a penta merge of KoboldAI's GPT-J classics; |
|
|
|
|
|
((Janeway + Shinen) + (Adventure + Skein)) + GPT-R. |
|
|
|
|
|
Janeway + Shinen is listed under JANIN-GPTJ. |
|
|
Adventure + Skein is listed under Adventien-GPTJ. |
|
|
|
|
|
GPT-R itself is a 60/40 merge of two instruct research models (see digitous/GPT-R for full credits). |
|
|
|
|
|
This 5x+ merge is not intended for minors, as it can produce NC-17+ content (mostly from Shinen). |
|
|
|
|
|
Javelin-R is a research artefact with dual purpose for entertainment as well as an intended |
|
|
example of potential value instruct can bring when combined with models of a different purpose |
|
|
through the use of weight sum merge technology. |
|
|
|
|
|
Mileage mat vary. No refunds best wishes. |
|
|
Mainly intended to be utilized with Open |
|
|
Source KoboldAI software. Optimal sampler |
|
|
and settings not determined. Feedback Welcome! |
|
|
|
|
|
https://github.com/KoboldAI/KoboldAI-Client |
|
|
# [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__Javelin-R) |
|
|
|
|
|
| Metric | Value | |
|
|
|-----------------------|---------------------------| |
|
|
| Avg. | 35.33 | |
|
|
| ARC (25-shot) | 41.64 | |
|
|
| HellaSwag (10-shot) | 69.01 | |
|
|
| MMLU (5-shot) | 30.7 | |
|
|
| TruthfulQA (0-shot) | 34.5 | |
|
|
| Winogrande (5-shot) | 64.8 | |
|
|
| GSM8K (5-shot) | 1.67 | |
|
|
| DROP (3-shot) | 5.01 | |
|
|
|
