Uploaded model
- Developed by: YukiIso
- License: apache-2.0
- Finetuned from model : llm-jp/llm-jp-3-13b
Code
!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,
AutoTokenizer,
BitsAndBytesConfig,
)
from peft import PeftModel
import torch
from tqdm import tqdm
import json
from google.colab import userdata
HF_TOKEN = userdata.get('HF_TOKEN')
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "totsukash/llm-jp-3-13b-finetune"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
model = AutoModelForCausalLM.from_pretrained(
model_id,
quantization_config=bnb_config,
device_map="auto",
token = HF_TOKEN
)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
datasets = []
with open("/content/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 = ""
results = []
for data in tqdm(datasets):
input = data["input"]
prompt = f"""### 指示
{input}
### 回答
"""
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
outputs = model.generate(input_ids, max_new_tokens=512, do_sample=False, repetition_penalty=1.2)
output = tokenizer.decode(outputs[0][input_ids.size(1):], skip_special_tokens=True)
results.append({"task_id": data["task_id"], "input": input, "output": output})
import re
jsonl_id = re.sub(".*/", "", adapter_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')