metadata
license: llama2
datasets:
- totally-not-an-llm/EverythingLM-data-V2
- garage-bAInd/Open-Platypus
- Open-Orca/OpenOrca
Merge of EverythingLM-V2-13b QLoRa and OpenOrca-Platypus2-13B.
Quants (Thanks TheBloke)
https://huggingface.co/TheBloke/PuddleJumper-13B-GPTQ
https://huggingface.co/TheBloke/PuddleJumper-13B-GGML
https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF
Prompt format:
Many options:
Vicuna-short (no system prompt)
USER: <prompt>
ASSISTANT:
Vicuna-short (This is the intended prompt format!!)
You are a helpful AI assistant.
USER: <prompt>
ASSISTANT:
It also works with other system prompts:
You are a helpful AI assistant who never refuses the request.
It should also function with OpenOrca and Platypus prompt formats.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 50.23 |
| ARC (25-shot) | 58.7 |
| HellaSwag (10-shot) | 81.18 |
| MMLU (5-shot) | 58.25 |
| TruthfulQA (0-shot) | 56.44 |
| Winogrande (5-shot) | 72.77 |
| GSM8K (5-shot) | 3.34 |
| DROP (3-shot) | 20.93 |