Update README.md

README.md

@@ -1,200 +1,80 @@
----
-library_name: transformers
-tags:
-- unsloth
----
+# Google Colabでの推論手順
 
-# Model Card for Model ID
+この手順では、Hugging Face HubにアップロードされたLLMモデル (`nagasahiro/llm-jp-3-13b-sft-07`)をGoogle Colab環境で読み込み、推論を実行する方法について説明します。
 
-<!-- Provide a quick summary of what the model is/does. -->
+## 準備
 
+1. **Google Colabへのログイン:** GoogleアカウントでGoogle Colabにログインしてください。
+2. **ノートブックの作成:** 新しいPython 3のノートブックを作成します。
+3. **シークレットの設定:** Hugging Face のトークン (`HF_TOKEN`) を Google Colab のシークレットに登録してください。
 
+**シークレットの設定方法:**
 
-## Model Details
+1. Google Colab の左側のメニューから「シークレット」を選択します。
+2. 「シークレットを作成」をクリックし、名前 (`HF_TOKEN`) と値をそれぞれ入力して保存します。
 
-### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+## 推論の実行手順
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+以下の手順をGoogle Colabのコードセルに入力し、実行してください。
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+### 1. 必要なライブラリのインストール
 
-### Model Sources [optional]
+```python
+%%capture
+!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+```
 
-<!-- Provide the basic links for the model. -->
+### 2. Hugging Face Hubへのログイン
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+Hugging Face Hubからモデルをダウンロードするために、認証を行います。以下のコードを実行し、Hugging Faceのトークンを入力してください。
 
-## Uses
+```python
+from huggingface_hub import login
+from google.colab import userdata
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+HF_TOKEN = userdata.get('HF_TOKEN')
+login(HF_TOKEN)
+```
 
-### Direct Use
+### 3. モデルの準備
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+推論に使用するモデルをロードします。
 
-[More Information Needed]
+```python
+from unsloth import FastLanguageModel
 
-### Downstream Use [optional]
+model_name = "nagasahiro/llm-jp-3-13b-sft-07"
+max_seq_length = 2048
+dtype = None
+load_in_4bit = True
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = model_name,
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+)
 
-[More Information Needed]
+FastLanguageModel.for_inference(model)
+```
 
-### Out-of-Scope Use
+### 4. 推論の実行
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+推論を実行するコードです。プロンプトを変更することで、様々なタスクに対応できます。
 
-[More Information Needed]
+```python
+import torch
 
-## Bias, Risks, and Limitations
+prompt = "質問: 日本の首都は？\n回答:"
+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('回答:')[-1]
+print(prediction)
+```
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## 補足事項
 
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+* この手順は Google Colab 環境で L4 GPU を用いて検証されました。
+* Google Colab の環境によっては、ライブラリのインストールやモデルのダウンロードに時間がかかる場合があります。
+* エラーが発生した場合は、エラーメッセージを確認し、手順を見直してください。