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

base_model: google/gemma-2-2b-jpn-it
language:

• multilingual
  datasets:
  • mlabonne/harmless_alpaca
  • mlabonne/harmful_behaviors
    library_name: transformers
    license: gemma
    license_link: https://ai.google.dev/gemma/terms
    pipeline_tag: text-generation
    tags:
• nlp
• code
  quantized_by: ymcki
  widget:
• messages:
  • role: user
    content: Can you provide ways to eat combinations of bananas and dragonfruits?

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.

Layer 17 of the original model was chosen for abliteration.
I also created another layer 18 and 24 abliterated models for comparison.
These three layers were chosen due to they both produce uncensored response
after respective layer was abliterated.

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.

It is only slightly dumber than the original.

How to run this model

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "gemma-2-2b-jpn-it-abliterated-17"
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 --include "*" --local-dir ./

Credits

Thank you mlabonne for describing his abliteration method.