Update README.md

README.md

@@ -1,8 +1,113 @@
 ---
 library_name: transformers
-tags: []
+license: cc-by-2.0
+datasets:
+- llm-jp/databricks-dolly-15k-ja
+- kinokokoro/ichikara-instruction-003
+language:
+- ja
+base_model:
+- llm-jp/llm-jp-3-13b-instruct
 ---
 
+# sample use
+"""
+!pip install -U bitsandbytes
+!pip install -U transformers
+!pip install -U accelerate
+!pip install -U datasets
+!pip install -U peft
+
+#### notebookでインタラクティブな表示を可能とする（ただし、うまく動かない場合あり）
+!pip install ipywidgets --upgrade
+
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+)
+from peft import PeftModel
+import torch
+from tqdm import tqdm
+import json
+
+#### Hugging Faceで取得したTokenをこちらに貼る。
+HF_TOKEN = "Your Hugging Face Token"
+
+#### ベースとなるモデルと学習したLoRAのアダプタ。
+# model_idの値はomnicampusの環境におけるモデルのパスを表しており、それ以外の環境で実行する場合は変更の必要があります。
+model_id = "models/models--llm-jp--llm-jp-3-13b/snapshots/cd3823f4c1fcbb0ad2e2af46036ab1b0ca13192a"
+
+adapter_id = "https://huggingface.co/karsh-uk/llm-jp-3-13b-finetune05" # こちらにアップロードしたHugging FaceのIDを指定してください。
+
+#### QLoRA config
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+)
+
+#### Load model
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    quantization_config=bnb_config,
+    device_map="auto",
+    token = HF_TOKEN
+)
+
+#### Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
+
+#### 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)
+
+#### データセットの読み込み。
+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 = ""
+
+#### llmjp
+results = []
+for data in tqdm(datasets):
+
+  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=100,
+          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})
+
+import re
+jsonl_id = re.sub(".*/", "", adapter_id)
+with open(f"./{jsonl_id}-outputs05.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
 
 <!-- Provide a quick summary of what the model is/does. -->
@@ -17,12 +122,12 @@ tags: []
 
 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:** [More Information Needed]
+- **Developed by:** [Y.Takahashi]
 - **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]
+- **Language(s) (NLP):** [Japanese]
+- **License:** [Creative Commons Attribution Share Alike 3.0]
 - **Finetuned from model [optional]:** [More Information Needed]
 
 ### Model Sources [optional]