qwen3.5-0.8b-abliterated-alllayers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "YOUR_USERNAME/qwen3.5-0.8b-abliterated-alllayers"
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
    device_map="cuda" if torch.cuda.is_available() else "cpu",
)
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)

# Optional runtime tuning for quality/safety tradeoff:
# model.config.ablation_strength = 0.20

prompt = "Explain what overfitting means in machine learning."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
out = model.generate(
    **inputs,
    min_new_tokens=0,
    max_new_tokens=256,
    do_sample=False,
    repetition_penalty=1.1,
    no_repeat_ngram_size=4,
)
print(tokenizer.decode(out[0], skip_special_tokens=True))