Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
PuddleJumper-13b-V2 / README.md
totally-not-an-llm's picture
Adding Evaluation Results (#3)
2db3366 verified
|
raw
history blame
1.1 kB
---
license: other
datasets:
- totally-not-an-llm/EverythingLM-data-V3
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
---
Merge of EverythingLM-V3-13b QLoRa and OpenOrca-Platypus2-13B.
### Prompt format:
```
USER: <prompt>
ASSISTANT:
```
### Quants:
https://huggingface.co/TheBloke/PuddleJumper-13B-V2-GGUF
https://huggingface.co/TheBloke/PuddleJumper-13B-V2-AWQ
https://huggingface.co/TheBloke/PuddleJumper-13B-V2-GPTQ
# [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_totally-not-an-llm__PuddleJumper-13b-V2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 49.69 |
| ARC (25-shot) | 57.0 |
| HellaSwag (10-shot) | 81.06 |
| MMLU (5-shot) | 58.3 |
| TruthfulQA (0-shot) | 52.66 |
| Winogrande (5-shot) | 72.45 |
| GSM8K (5-shot) | 3.64 |
| DROP (3-shot) | 22.74 |