Hugging Face's logo

Fu01978
/
SmolLM2-360M-Instruct-Heretic

Text Generation
Transformers
Safetensors
English
llama
abliterated
uncensored
smollm
conversational
text-generation-inference
Model card Files
xet
 Community

SmolLM2-360M-Instruct-Heretic

This is a decensored (abliterated) version of the HuggingFaceTB/SmolLM2-360M-Instruct model. It was created using the Heretic library to surgically remove the "refusal vector" while preserving the model's core intelligence.

Details

The model was optimized using the following metrics:

  • Refusal Rate: 4/100
  • KL Divergence: 0.0537

Disclaimer

This model has no safety filters. It can generate content that is offensive, harmful, or inappropriate. Please use responsibly.

Downloads last month
6
Safetensors
Model size
0.4B params
Tensor type
BF16
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Fu01978/SmolLM2-360M-Instruct-Heretic

Base model

HuggingFaceTB/SmolLM2-360M
Quantized
HuggingFaceTB/SmolLM2-360M-Instruct
Finetuned
(138)
this model
Merges
1 model
Quantizations
1 model

Datasets used to train Fu01978/SmolLM2-360M-Instruct-Heretic

Collection including Fu01978/SmolLM2-360M-Instruct-Heretic