gemma-2-9b-nyan100 / README.md
Hizaneko's picture
Update README.md
84762cd verified
---
library_name: transformers
tags:
- unsloth
license: apache-2.0
datasets:
- llm-jp/magpie-sft-v1.0
language:
- ja
base_model:
- google/gemma-2-9b
---
### Uploaded model
- **Developed by:** [Hizaneko]
- **License:** [apache-2.0]
- **Finetuned from model:** [google/gemma-2-9b]
## Hugging Faceにアップロードしたモデルを用いてELYZA-tasks-100-TVの出力を得るためのコードです。
## Uses
%%capture
!pip install unsloth
!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
!pip install -U torch
!pip install -U peft
from unsloth import FastLanguageModel
from peft import PeftModel
import torch
import json
from tqdm import tqdm
import re
from google.colab import userdata
HF_TOKEN=userdata.get('HF_TOKEN')
### ベースとなるモデルと学習したLoRAのアダプタ(Hugging FaceのIDを指定)。
### HFからモデルリポジトリをダウンロード
!huggingface-cli login --token $HF_TOKEN
!huggingface-cli download google/gemma-2-9b --local-dir gemma-2-9b/
model_id = "./gemma-2-9b"
adapter_id = "Hizaneko/gemma-2-9b-nyan100"
### unslothのFastLanguageModelで元のモデルをロード。
dtype = None
load_in_4bit = True
model, tokenizer = FastLanguageModel.from_pretrained(
model_name=model_id,
dtype=dtype,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
)
# 元のモデルにLoRAのアダプタを統合。
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
# 事前にデータをアップロードしてください。
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 = ""
### 推論するためにモデルのモードを変更
FastLanguageModel.for_inference(model)
results = []
for dt in tqdm(datasets):
input = dt["input"]
prompt = f"""### 指示\n{input} 簡潔に回答してください \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})
### 結果をjsonlで保存。
json_file_id = re.sub(".*/", "", adapter_id)
with open(f"/content/{json_file_id}_output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')