--- tags: - text-generation license: cc-by-nc-sa-4.0 language: - ko base_model: hyeogi/SOLAR-10.7B-dpo-v0.1 pipeline_tag: text-generation datasets: - jojo0217/korean_rlhf_dataset --- # **DataVortexS-10.7B-v0.3** ## Our Team | Research & Engineering | Product Management | | :--------------------: | :----------------: | | Kwangseok Yang | Seunghyun Choi | | Jeongwon Choi | Hyoseok Choi | ## **Model Details** ### **Base Model** [hyeogi/SOLAR-10.7B-dpo-v0.1](https://huggingface.co/hyeogi/SOLAR-10.7B-dpo-v0.1) ### **Trained On** - **OS**: Ubuntu 20.04 - **GPU**: H100 80GB 1ea - **transformers**: v4.36.2 ### **Dataset** - [jojo0217/korean_rlhf_dataset](https://huggingface.co/datasets/jojo0217/korean_rlhf_dataset) ### **Instruction format** It follows **Alpaca** format. E.g. ```python text = """\ 당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다. ### Instruction: 대한민국의 수도는 어디야? ### Response: 대한민국의 수도는 서울입니다. ### Instruction: 서울 인구는 총 몇 명이야? """ ``` ## **Model Benchmark** ### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)** | Task | 0-shot | 5-shot | 10-shot | 50-shot | | :--------------- | -------------: | -------------: | ------------: | -------------: | | kobest_boolq | 0.606754 | 0.553485 | 0.583201 | 0.587602 | | kobest_copa | 0.603643 | 0.625567 | 0.618533 | 0.627404 | | kobest_hellaswag | 0.360793 | 0.366002 | 0.37105 | 0.357439 | | kobest_sentineg | 0.652929 | 0.751097 | 0.742426 | 0.760152 | | **Average** | **0.55602975** | **0.57403775** | **0.5788025** | **0.58314925** | ### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)** | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 | | ------: | -----: | -----------: | ------: | ------------: | --------------: | | 37.57 | 33.87 | 42.47 | 28.21 | 46.09 | 37.19 | ## **Implementation Code** This model contains the chat_template instruction format. You can use the code below. ```python from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # the device to load the model onto model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-v0.3") tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-v0.3") messages = [ {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."}, {"role": "user", "content": "대한민국의 수도는 어디야?"}, {"role": "assistant", "content": "대한민국의 수도는 서울입니다."}, {"role": "user", "content": "서울 인구는 총 몇 명이야?"} ] encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") model_inputs = encodeds.to(device) model.to(device) generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) decoded = tokenizer.batch_decode(generated_ids) print(decoded[0]) ``` ## **License** The model is licensed under the [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.