Uploaded model
- Developed by: formapproval
- License: apache-2.0
- Finetuned from model : llm-jp/llm-jp-3-13b
使い方
前提：Omnicampus上で行う・elyza-tasks-100-TV_0.jsonlをルートディレクトリ上に配置
手順 以下のコードをipynbファイルで、ルートディレクトリ上で実行
!pip install -U pip
!pip install -U transformers
!pip install -U bitsandbytes
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft
!pip install -U trl
!pip install -U wandb
!pip install ipywidgets --upgrade
from transformers import AutoModelForCausalLM
import os, torch, gc
from datasets import load_dataset
import bitsandbytes as bnb
from trl import SFTTrainer
base_model_id = "llm-jp/llm-jp-3-13b"
HF_TOKEN="~~~"#オープンサイトでは伝えられなかったので、後で伝える形になります
model = AutoModelForCausalLM.from_pretrained(
base_model_id,
token=HF_TOKEN,
quantization_config=bnb_config,
device_map="auto"
)
import json
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 data in tqdm(datasets):
input = data["input"]
prompt = f"""### 指示
{input}
"""
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=100,
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})
import re
jsonl_id = re.sub(".*/", "", new_model_id)
with open(f"./{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')