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

Step 2: Load Required Libraries

python

from unsloth import FastLanguageModel
import torch
import json

Step 3: Load the Model

Specify the base model and the adapter for LoRA fine-tuning. Replace <adapter_id> and <HF_TOKEN> with appropriate values.

python

# Base model
model_name = "kkkeee/llm-jp-3-13b-it15"

# Hugging Face Token
HF_TOKEN = "<your_hf_token>"  # Obtain token from https://huggingface.co/settings/tokens

# Load base model using Unsloth
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)

Step 4: Load Dataset

Prepare your dataset in .jsonl format and upload it to your environment.

python

# Load task data
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 = ""

Step 5: Perform Inference

Set the model to inference mode and generate predictions.

python

from tqdm import tqdm

# 推論
results = []
for data in tqdm(datasets):
  input = data["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)
  output = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]

  results.append({"task_id": data["task_id"], "input": input, "output": output})

Step 6: Save Results

Save the inference results to a .jsonl file. Replace <adapter_id> with the appropriate identifier.

python

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