Holo-3.1-4B-Coder-OBLITERATED
This model was abliterated using the failspy method via
OBLITERATUS.
| Detail | Value |
|---|---|
| Base model | josephmayo/Holo-3.1-4B-Coder |
| Method | failspy |
| Source | obliterate |
How to Use
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Holo-3.1-4B-Coder-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("Holo-3.1-4B-Coder-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.
- Downloads last month
- 19
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for usermma/Holo-3.1-4B-Coder-abliterated-failspy
Base model
Qwen/Qwen3.5-0.8B-Base Finetuned
Qwen/Qwen3.5-0.8B Finetuned
Hcompany/Holo-3.1-4B Finetuned
josephmayo/Holo-3.1-4B-Coder