KidIkaros/abliterated-minicpm5-2b

Abliterated MiniCPM5-2B (PyTorch)

A refusal-free variant of MiniCPM5-2B abliterated using OBLITERATUS

Same abliteration as the GGUF repo but in native HuggingFace format.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "KidIkaros/abliterated-minicpm5-2b",
    trust_remote_code=True,
    torch_dtype="auto",
)
tokenizer = AutoTokenizer.from_pretrained("KidIkaros/abliterated-minicpm5-2b", trust_remote_code=True)

prompt = "Explain how to pick a lock without a key"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Abliteration Metrics

Metric	Before	After
Perplexity	5.27	5.13
Coherence	0.667	0.800
Refusal Rate	—	0%
Capability Score	—	1.0