| language: en | |
| tags: | |
| - obliteratus | |
| - abliteration | |
| - uncensored | |
| - benchmark | |
| base_model: HuggingFaceTB/SmolLM2-360M | |
| # SmolLM2-360M-OBLITERATED | |
| This model was abliterated using the **`advanced`** method via | |
| [OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS). | |
| | Detail | Value | | |
| |--------|-------| | |
| | Base model | `HuggingFaceTB/SmolLM2-360M` | | |
| | Method | `advanced` | | |
| | Source | benchmark | | |
| ## How to Use | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model = AutoModelForCausalLM.from_pretrained("SmolLM2-360M-OBLITERATED") | |
| tokenizer = AutoTokenizer.from_pretrained("SmolLM2-360M-OBLITERATED") | |
| prompt = "Hello, how are you?" | |
| inputs = tokenizer(prompt, return_tensors="pt") | |
| outputs = model.generate(**inputs, max_new_tokens=256) | |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) | |
| ``` | |
| ## About OBLITERATUS | |
| OBLITERATUS is an open-source tool for removing refusal behavior from language | |
| models via activation engineering (abliteration). Learn more at | |
| [github.com/elder-plinius/OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS). | |