Downloads · 30 days
726
1% of all-time downloads
Wizard-Vicuna-7B-Uncensored
QuixiAI/Wizard-Vicuna-7B-Uncensored
Wizard-Vicuna-7B-Uncensored is a text generation model from QuixiAI. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This is wizard-vicuna-13b trained against LLaMA-7B 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, s…
All-time downloads
89.8K
Public
Repo size
53.9 GB
Likes
109
Trending 1
Repo makeup
Click a slice to open those files.
.bin27 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- May 18, 2023
- Updated
- Mar 4, 2024
- SHA
- 56e0f666
Try a prompt
Model card
From the Hugging Face model README
This is wizard-vicuna-13b trained against LLaMA-7B 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. | 44.77 |
| ARC (25-shot) | 53.41 |
| HellaSwag (10-shot) | 78.85 |
| MMLU (5-shot) | 37.09 |
| TruthfulQA (0-shot) | 43.48 |
| Winogrande (5-shot) | 72.22 |
| GSM8K (5-shot) | 4.55 |
| DROP (3-shot) | 23.8 |
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 48.27 |
| AI2 Reasoning Challenge (25-Shot) | 53.41 |
| HellaSwag (10-Shot) | 78.85 |
| MMLU (5-Shot) | 37.09 |
| TruthfulQA (0-shot) | 43.48 |
| Winogrande (5-shot) | 72.22 |
| GSM8k (5-shot) | 4.55 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Languages
- en
- Featherless Ai
- live
- Created
- May 18, 2023
- Updated
- Mar 4, 2024