mss6/f4

Sample code

!pip install -U bitsandbytes
!pip install -U transformers
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft

!pip install ipywidgets --upgrade

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
)
from peft import PeftModel
import torch
from tqdm import tqdm
import json
import re
from google.colab import files

HF_TOKEN = "YOUR TOKEN"
your_path = '/elyza-tasks-100-TV_0.jsonl'

model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "mss6/f4" 

model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)

datasets = []
with open(your_path, "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 i in tqdm(range(100)):
  data = datasets[i]
  input = data["input"]

  prompt = f"""### 指示
  {input}
  ### 回答
  """

  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
  attention_mask = torch.ones_like(tokenized_input)

  with torch.no_grad():
      outputs = model.generate(
          tokenized_input,
          attention_mask=attention_mask,
          max_new_tokens=1000,
          do_sample=False,
          repetition_penalty=1.2,
          pad_token_id=tokenizer.eos_token_id
      )[0]
  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)

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

jsonl_id = re.sub(".*/", "", 'ans')
with open(f"/content/drive/MyDrive/{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)
        f.write('\n')

Datasets

Instruction tuning

The models have been fine-tuned on the following datasets.

Language	Dataset	url
Japanese	ichikara-instruction	ichikara-instruction
	Synthesized data from Elyza-tasks-100	Elyza-tasks-100