This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

"""python, Google Colab %%capture !pip install unsloth !pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"

from unsloth import FastLanguageModel import torch import json

model_name = "YOUR_ACCOUNT/llm-jp-3-13b-finetune-2"

max_seq_length = 2048 dtype = None load_in_4bit = True

model, tokenizer = FastLanguageModel.from_pretrained( model_name = model_name, max_seq_length = max_seq_length, dtype = dtype, load_in_4bit = load_in_4bit, token = "HF_TOKEN", ) FastLanguageModel.for_inference(model)

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 = ""

from tqdm import tqdm

results = [] for dt in tqdm(datasets): input = dt["input"]

prompt = f"""### 指示\n{input}\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})

with open(f"/content/{model_name}_output.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n') """