--- language: - multilingual license: gemma library_name: transformers tags: - nlp - code base_model: google/gemma-2-2b-jpn-it datasets: - mlabonne/orpo-dpo-mix-40k license_link: https://ai.google.dev/gemma/terms pipeline_tag: text-generation quantized_by: ymcki widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits? model-index: - name: gemma-2-2b-jpn-it-abliterated-17-ORPO results: - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 49.48 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 14.92 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 2.87 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 3.24 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 5.67 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 13.18 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO name: Open LLM Leaderboard --- Original model: https://huggingface.co/google/gemma-2-2b-jpn-it ## Prompt format ``` user {prompt} model model ``` Note that this model does not support a System prompt. This is abliterated model of [google/gemma-2-2b-jpn-it](https://huggingface.co/google/gemma-2-2b-jpn-it) using the [method](https://medium.com/@mlabonne/uncensor-any-llm-with-abliteration-d30148b7d43e) described by mlabonne. Layer 17 of the original model was chosen for abliteration. I also created another layer 18 abliterated model for comparison. ORPO fine tuning was performed for four epoches. | Epoch | loss | eval_loss | | ----- | ---- | --------- | | 1 | 1.20152769684791564 | 1.0501047372817993 | | 2 | 1.25755584239959716 | 1.0144596099853516 | | 3 | 0.93099724054336543 | 0.9957754611968994 | | 4 | 0.88664623498916623 | 0.9857067465782166 | 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](https://towardsdatascience.com/fine-tune-llama-3-with-orpo-56cfab2f9ada) but the input model was read into VRAM by [unsloth](https://github.com/unslothai/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](https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/google/gemma-2-2b-jpn-it/results_2024-10-15T15-21-39.173019.json) | 30.82 | 54.11 | 41.43 | 0.0 | 27.52 | 37.17 | 24.67 | | [gemma-2-2b-jpn-it-abliterated-17-ORPO](https://huggingface.co/datasets/open-llm-leaderboard/results/raw/main/ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO/results_2024-10-20T02-46-59.069357.json) | 29.99 | 50.94 | 38.59 | 2.87 | 27.43 | 38.23 | 21.86 | | [gemma-2-2b-jpn-it-abliterated-17](https://huggingface.co/datasets/open-llm-leaderboard/results/raw/main/ymcki/gemma-2-2b-jpn-it-abliterated-17/results_2024-10-18T15-18-46.821674.json) | 30.29 | 52.65 | 40.46 | 0.0 | 27.18 | 36.90 | 24.55 | | [gemma-2-2b-jpn-it-abliterated-18](https://huggingface.co/datasets/open-llm-leaderboard/results/raw/main/ymcki/gemma-2-2b-jpn-it-abliterated-18/results_2024-10-18T15-41-42.399571.json) | 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 ```py from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model_id = "gemma-2-2b-jpn-it-abliterated-17-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-17-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. # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ymcki__gemma-2-2b-jpn-it-abliterated-17-ORPO) | Metric |Value| |-------------------|----:| |Avg. |14.89| |IFEval (0-Shot) |49.48| |BBH (3-Shot) |14.92| |MATH Lvl 5 (4-Shot)| 2.87| |GPQA (0-shot) | 3.24| |MuSR (0-shot) | 5.67| |MMLU-PRO (5-shot) |13.18|