Update README.md

README.md

@@ -4,7 +4,69 @@ tags: []
 ---
 # Sample code
 ```python    ```
-a+b
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+)
+from peft import PeftModel
+import torch
+from tqdm import tqdm
+import json
+import re
+from google.colab import files
+
+HF_TOKEN = "YOUR TOKEN"
+your_path = '/elyza-tasks-100-TV_0.jsonl'
+
+model_id = "llm-jp/llm-jp-3-13b"
+adapter_id = "mss6/f4" 
+
+model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
+
+datasets = []
+with open(your_path, "r") as f:
+    item = ""
+    for line in f:
+      line = line.strip()
+      item += line
+      if item.endswith("}"):
+        datasets.append(json.loads(item))
+        item = ""
+
+from tqdm import tqdm
+
+results = []
+for i in tqdm(range(100)):
+  data = datasets[i]
+  input = data["input"]
+
+  prompt = f"""### 指示
+  {input}
+  ### 回答
+  """
+
+  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
+  attention_mask = torch.ones_like(tokenized_input)
+
+  with torch.no_grad():
+      outputs = model.generate(
+          tokenized_input,
+          attention_mask=attention_mask,
+          max_new_tokens=1000,
+          do_sample=False,
+          repetition_penalty=1.2,
+          pad_token_id=tokenizer.eos_token_id
+      )[0]
+  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
+
+  results.append({"task_id": data["task_id"], "input": input, "output": output})
+
+jsonl_id = re.sub(".*/", "", 'ans')
+with open(f"/content/drive/MyDrive/{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
+    for result in results:
+        json.dump(result, f, ensure_ascii=False)  # ensure_ascii=False for handling non-ASCII characters
+        f.write('\n')
 ``` ```
 # Model Card for Model ID