ymcki/gemma-2-2b-jpn-it-abliterated-17-18-24

Original model: https://huggingface.co/google/gemma-2-2b-jpn-it

Prompt format

<start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model
<end_of_turn>
<start_of_turn>model

Note that this model does not support a System prompt.

This is abliterated model of google/gemma-2-2b-jpn-it using the method described by mlabonne.

This time multiple Layers are abliterated to study its performance. Layer 17, 18 and 24 of the original model were chosen for abliteration.

It is uploaded here to be evaluated by the Open LLM Leaderboard to see how brain damaged it is compared to the original model.

ORPO fine tuning is currently underway to see if it can regain its sanity. You can play with this model first or wait until I am done with the fine tuning.

Benchmark (100.0*raw scores only)

Click on the model name go to the raw score json generated by Open LLM Leaderboard.

Model	Average	IFEval	BHH	Math Lv5	GPQA	MUSR	MMLU-PRO
gemma-2-2b-jpn-it	30.82	54.11	41.43	0.0	27.52	37.17	24.67
gemma-2-2b-jpn-it-abliterated-17	30.29	52.65	40.46	0.0	27.18	36.90	24.55
gemma-2-2b-jpn-it-abliterated-18	30.61	53.02	40.96	0.0	27.35	37.30	25.05
gemma-2-2b-jpn-it-abliterated-24	30.61	51.37	40.77	0.0	27.77	39.02	24.73
gemma-2-2b-jpn-it-abliterated-17-18-24	29.17	51.33	37.82	0.0	28.10	34.92	22.82

It is only slightly dumber than the original for models that have only one layer abliterated. For the model with three layers abiliterated, the brain damage is more significant.

How to run this model

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "gemma-2-2b-jpn-it-abliterated-17-18-24"
dtype = torch.bfloat16

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

chat = [
    { "role": "user", "content": "Write a hello world program" },
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download ymcki/gemma-2-2b-jpn-it-abliterated-17-18-24 --include "*" --local-dir ./

Credits

Thank you mlabonne for describing his abliteration method.