ymcki/gemma-2-2b-jpn-it-abliterated-18-ORPO

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 18 of the original model was chosen for abliteration. I also created another layer 17 abliterated model for comparison.

ORPO fine tuning was performed for four epoches.

Epoch	loss	eval_loss
1	1.0452101707458496	1.0170862674713135
2	0.81533865332603454	0.9825302958488464
3	1.15400108695030208	0.9852740168571472
4	0.76560704708099362	0.9880287051200867

The fine tuned model is uploaded here to be evaluated by the Open LLM Leaderboard to see if the slightly brain damaged non-ORPO model can be healed. Again, the fine tuning method is also based on one described by mlabonne but the input model was read into VRAM by unsloth to allow using the full 40k dataset to run on a single 3090.

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-ORPO	29.99	50.94	38.59	2.87	27.43	38.23	21.86
gemma-2-2b-jpn-it-abliterated-18-ORPO	29.94	48.97	40.18	3.02	26.17	39.42	21.85
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

Looks like fine tuning is probably not enough. May need to run more epoches.

How to run this model

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "gemma-2-2b-jpn-it-abliterated-18-ORPO"
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-18-ORPO --include "*" --local-dir ./

Credits

Thank you mlabonne for describing his fine tuning method.

Thanks FullOf_Bad_Ideas from LocalLlama for the suggestion of using unsloth to save VRAM.