Update README.md

README.md

@@ -18,12 +18,76 @@ base_model:
 - trl==0.12.2
 - transformers<4.47.0
 - tokenizers==0.21.0
+- bitsandbytes==0.45.0
+- peft==0.14.0
+- datasets==3.2.0
 
 ## Usage
 
+Google Colaboratory（L4 GPU）にて実行
+
+```py
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+    TrainingArguments,
+    logging,
+)
+from peft import (
+    LoraConfig,
+    PeftModel,
+    get_peft_model,
+)
+
+import os, torch, gc, json
+from tqdm import tqdm
+from datasets import load_dataset
+import bitsandbytes as bnb
+from trl import SFTTrainer
+from google.colab import userdata
+
+# Hugging Face Token
+os.environ["LANGCHAIN_API_KEY"] = userdata.get("LANGCHAIN_API_KEY")
+os.environ["HF_TOKEN"] = userdata.get("HF_TOKEN")
+```
+
+```py
+
+# 推論データ準備
+datasets = []
+
+inference_data_path = '/content/drive/MyDrive/your_path'
+with open(f"{inference_data_path}/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 = ""
+
+# モデルとトークナイザー準備
+new_model_id = "yottan-wywy/llm-jp-3-13b-instruct-finetune_1217"
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    new_model_id,
+    quantization_config=bnb_config,
+    device_map="auto"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(new_model_id, trust_remote_code=True)
+```
+
 ```py
 results = []
-system_text = "以下は、タスクを説明する指示です。要求を適切に満たす回答を**簡潔に**書いてください。回答の後ろに、回答の理由を**1文で**書いてください。"
+system_text = "以下は、タスクを説明する指示です。要求を適切に満たす回答を**簡潔に**書きなさい。"
 for data in tqdm(datasets):
 
   input_text = data["input"]