This is wizard-vicuna-13b trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
Shout out to the open source AI/ML community, and everyone who helped me out.
Note:
An uncensored model has no guardrails.
You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.
Publishing anything this model generates is the same as publishing it yourself.
You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 53.44 |
| ARC (25-shot) | 62.12 |
| HellaSwag (10-shot) | 83.45 |
| MMLU (5-shot) | 58.24 |
| TruthfulQA (0-shot) | 50.81 |
| Winogrande (5-shot) | 78.45 |
| GSM8K (5-shot) | 14.25 |
| DROP (3-shot) | 26.74 |
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 57.89 |
| AI2 Reasoning Challenge (25-Shot) | 62.12 |
| HellaSwag (10-Shot) | 83.45 |
| MMLU (5-Shot) | 58.24 |
| TruthfulQA (0-shot) | 50.81 |
| Winogrande (5-shot) | 78.45 |
| GSM8k (5-shot) | 14.25 |
- Downloads last month
- 0
Dataset used to train mav23/Wizard-Vicuna-30B-Uncensored-GGUF
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard62.120
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard83.450
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard58.240
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard50.810
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.450
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard14.250