Silicon-Monika-7b
- Model fine-tuned for Natsuki character from DDLC per a request
- Base: SanjiWatsuki/Silicon-Maid-7B (Mistral)
- GGUF
USAGE
For best results: replace "Human" and "Assistant" with "Player" and "Natsuki" like so:
\nPlayer: (prompt)\nNatsuki:
HYPERPARAMS
- Trained for 1 epoch
- rank: 32
- lora alpha: 32
- lora dropout: 0
- lr: 2e-4
- batch size: 2
- grad steps: 4
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
WARNINGS AND DISCLAIMERS
This model is meant to closely reflect the characteristics of Natsuki. Despite this, there is always the chance that "Natsuki" will hallucinate and get information about herself wrong or act out of character.
Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.70 |
| AI2 Reasoning Challenge (25-Shot) | 65.19 |
| HellaSwag (10-Shot) | 83.98 |
| MMLU (5-Shot) | 62.88 |
| TruthfulQA (0-shot) | 57.85 |
| Winogrande (5-shot) | 78.69 |
| GSM8k (5-shot) | 57.62 |
- Downloads last month
- 1,142
Unable to determine this model’s pipeline type. Check the
docs
.
Finetuned from
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard65.190
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard83.980
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard62.880
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard57.850
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.690
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard57.620