Instructions to use Yu339/gemma-2-9b-it14_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Yu339/gemma-2-9b-it14_lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Yu339/gemma-2-9b-it14_lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use Yu339/gemma-2-9b-it14_lora with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Yu339/gemma-2-9b-it14_lora to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Yu339/gemma-2-9b-it14_lora to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Yu339/gemma-2-9b-it14_lora to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Yu339/gemma-2-9b-it14_lora", max_seq_length=2048, )
Model Card for Model ID
東京大学松尾・岩澤研究室(松尾研)大規模言語モデル Deep Learning 応用講座 2024 におけるコンペティション提出物です。 elyza/ELYZA-tasks-100を参考に独自に作成した問題に対する出力を行います。
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by: Yu339
- **Model type: ベースモデル: google/gemma-2-9b
- **License: Gemma License ライセンス
- **Finetuned from model : LoRAによるファインチューニング
Model Sources
- **Repository: kajuma/Llama-SFT-3000https://huggingface.co/datasets/kajuma/Llama-SFT-3000
- **Lisence: The instructions of this dataset are generated by Tanuki-8B-dpo-v1.0 and the outputs are generated by Llama-3.1-SuperSwallow-70B-Instruct-v0.1. Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
How to Get Started with the Model
Use the code below to get started with the model.
## 必要なライブラリをインストール
!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
## 必要なライブラリを読み込み
from unsloth import FastLanguageModel
from peft import PeftModel
import torch
import json
from tqdm import tqdm
import re
## Hugging Face Token を指定。
# 下記の URL から Hugging Face Token を取得できますので下記の HF_TOKEN に入れてください。
# https://huggingface.co/settings/tokens
HF_TOKEN = "your-token" #@param {type:"string"}
## 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)
!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 = "Yu339/gemma-2-9b-it14_lora"
## unslothのFastLanguageModelで元のモデルをロード
dtype = None # Noneにしておけば自動で設定
load_in_4bit = True # 今回は13Bモデルを扱うため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のアダプタ統合
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
## タスクとなるデータの読み込み
# 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 = ""
## モデルを用いてタスクの推論。
# 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}\n### 回答\n"""
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens = 1024, 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。
# ここではadapter_idを元にファイル名を決定しているが、ファイル名は任意で問題なし。
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')
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support