Ministral-3-14B-abliterated

This is an abliterated (uncensored) version of Ministral-3-14B-Instruct-2512 created using the abliteration technique.

What is Abliteration?

Abliteration is a technique that removes refusal behavior from language models by identifying and modifying the internal representations responsible for refusals. This creates a model that is more willing to engage with a wider range of topics.

This model was abliterated using llm-abliteration by grimjim, which implements norm-preserving biprojected abliteration.

Model Details

Base Model: mistralai/Ministral-3-14B-Instruct-2512
Parameters: ~14B
Format: SafeTensors (BF16)
License: Apache 2.0

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "jenerallee78/Ministral-3-14B-abliterated"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Hello, how are you?"}
]

input_ids = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

GGUF Versions

For GGUF quantized versions compatible with llama.cpp, see: jenerallee78/Ministral-3-14B-abliterated-GGUF

Disclaimer

This model is provided for research and educational purposes. Users are responsible for ensuring their use complies with applicable laws and ethical guidelines.

What is Abliteration?

This model was abliterated using llm-abliteration by grimjim, which implements norm-preserving biprojected abliteration.

Further Reading

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "jenerallee78/Ministral-3-14B-abliterated" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto" ) messages = [ {"role": "user", "content": "Hello, how are you?"} ] input_ids = tokenizer.apply_chat_template( messages, return_tensors="pt" ).to(model.device) outputs = model.generate( input_ids, max_new_tokens=512, do_sample=True, temperature=0.7 ) print(tokenizer.decode(outputs[0], skip_special_tokens=True))