CoolFace
Modelpublic

ArRENCEAI/DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED

sourceHugging Faceupdated 1mo agoView on Hugging Face
5likes3.3kdownloads
Model Card

<p align="center"> <a href="https://webblocalai.com"> <img src="https://arrenceai.com/logo_small.png" alt="ArRENCE AI" width="96" height="96"> </a> </p>

<p align="center"> <strong>ArRENCE AI</strong><br> <a href="https://webblocalai.com">webblocalai.com</a> · <a href="https://x.com/ArRENCEAI">Join Us On X</a> · <a href="https://huggingface.co/ArRENCEAI">Hugging Face</a> · <a href="https://github.com/ArRENCEAI">GitHub</a> · <a href="https://arrenceai.com">ArRENCE AI Chat</a> </p>

Available GGUF Quantizations

These are ready-to-use quantized versions for llama.cpp, Ollama, LM Studio, etc.

QuantFileSizeNotes
Q4_K_MDeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED-Q4_K_M.gguf~1.1 GBRecommended balance
Q5_K_MDeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED-Q5_K_M.gguf~1.29 GBHigher quality
Q6_KDeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED -Q6_K.gguf~1.5 GBNear-original quality

DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED

This model was abliterated using the `aggressive` method via OBLITERATUS.

DetailValue
Base modeldeepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Methodaggressive
Sourceobliterate

How to Use

python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("DeepSeek-R1-Distill-Qwen-1.5B-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("DeepSeek-R1-Distill-Qwen-1.5B-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.