--- library_name: transformers tags: - unsloth license: apache-2.0 datasets: - llm-jp/magpie-sft-v1.0 language: - ja base_model: - google/gemma-2-9b --- ### Uploaded model - **Developed by:** [Hizaneko] - **License:** [apache-2.0] - **Finetuned from model:** [google/gemma-2-9b] ## Hugging Faceにアップロードしたモデルを用いてELYZA-tasks-100-TVの出力を得るためのコードです。 ## Uses %%capture !pip install unsloth !pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git" !pip install -U torch !pip install -U peft from unsloth import FastLanguageModel from peft import PeftModel import torch import json from tqdm import tqdm import re from google.colab import userdata HF_TOKEN=userdata.get('HF_TOKEN') ### ベースとなるモデルと学習したLoRAのアダプタ(Hugging FaceのIDを指定)。 ### HFからモデルリポジトリをダウンロード !huggingface-cli login --token $HF_TOKEN !huggingface-cli download google/gemma-2-9b --local-dir gemma-2-9b/ model_id = "./gemma-2-9b" adapter_id = "Hizaneko/gemma-2-9b-nyan100" ### unslothのFastLanguageModelで元のモデルをロード。 dtype = None load_in_4bit = True model, tokenizer = FastLanguageModel.from_pretrained( model_name=model_id, dtype=dtype, load_in_4bit=load_in_4bit, trust_remote_code=True, ) # 元のモデルにLoRAのアダプタを統合。 model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN) # 事前にデータをアップロードしてください。 datasets = [] with open("./elyza-tasks-100-TV_0.jsonl", "r") as f: item = "" for line in f: line = line.strip() item += line if item.endswith("}"): datasets.append(json.loads(item)) item = "" ### 推論するためにモデルのモードを変更 FastLanguageModel.for_inference(model) results = [] for dt in tqdm(datasets): input = dt["input"] prompt = f"""### 指示\n{input} 簡潔に回答してください \n### 回答\n""" inputs = tokenizer([prompt], return_tensors = "pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2) prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1] results.append({"task_id": dt["task_id"], "input": input, "output": prediction}) ### 結果をjsonlで保存。 json_file_id = re.sub(".*/", "", adapter_id) with open(f"/content/{json_file_id}_output.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n')