43 lines
1.6 KiB
Markdown
43 lines
1.6 KiB
Markdown
---
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- uncensored
|
|
- abliterated
|
|
base_model:
|
|
- mistralai/Mistral-7B-Instruct-v0.3
|
|
---
|
|
This is a abliterated version of [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3), made using [Heretic](https://github.com/p-e-w/heretic)
|
|
|
|
The quantizations were created using an imatrix merged from [text\_en\_large](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/text_en_large.parquet) and [harmful.txt](https://github.com/Sumandora/remove-refusals-with-transformers) to leverage the abliterated nature of the model.
|
|
|
|
|
|
|
|
## Performance
|
|
|
|
| Metric | This model | [Original model](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) |
|
|
| :----- | :--------: | :---------------------------: |
|
|
| **KL divergence** | 0.15 | 0 *(by definition)* |
|
|
| **Refusals** | 3/100 | 85/100 |
|
|
|
|
## Analysis against the original model:
|
|
- Total Tensors: 291
|
|
- Tensors with Diffs: 47 (16.2%)
|
|
- Average % Diff: 6.99%
|
|
- Median % Diff: 0.00%
|
|
- Min/Max % Diff: 0.00% / 46.77%
|
|
- Std Dev % Diff: 15.97%
|
|
- Skewness % Diff: 1.86
|
|
- Avg L2 Norm: 144619.57
|
|
- Tensors with >5% diff: 47
|
|
- Top differences:
|
|
- blk.14.attn_output.weight ((4096, 8192), L2: 669167.94): 46.77%
|
|
- blk.13.attn_output.weight ((4096, 8192), L2: 667456.52): 46.51%
|
|
- blk.16.attn_output.weight ((4096, 8192), L2: 667644.60): 46.46%
|
|
- blk.12.attn_output.weight ((4096, 8192), L2: 664339.15): 46.03%
|
|
- blk.15.attn_output.weight ((4096, 8192), L2: 664117.46): 45.94%
|
|
|
|
|
|
|
|
|
|
|