Update README.md

README.md

@@ -34,6 +34,108 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **Paper [optional]:** [More Information Needed]
 - **Demo [optional]:** [More Information Needed]
 
+## Usage
+
+```python
+!pip install -U bitsandbytes
+!pip install -U transformers
+!pip install -U accelerate
+!pip install -U datasets
+```
+
+```python
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+)
+import torch
+from tqdm import tqdm
+import json
+```
+
+```python
+HF_TOKEN = "YOUR-HF-TOKEN"
+```
+
+```python
+base_model_id = "llm-jp/llm-jp-3-13b"
+adapter_id = "koichi-sumizaki/llm-jp-3-13b-it2024-12-14_lora" 
+```
+
+```python
+# QLoRA config
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+)
+```
+
+```python
+# Load model
+model = AutoModelForCausalLM.from_pretrained(
+    base_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)
+```
+
+```python
+datasets = []
+with open("./YOUR-DATA.jsonl", "r") as f:
+    item = ""
+    for line in f:
+      line = line.strip()
+      item += line
+      if item.endswith("}"):
+        datasets.append(json.loads(item))
+        item = ""
+```
+
+```python
+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)
+  with torch.no_grad():
+      outputs = model.generate(
+          tokenized_input,
+          max_new_tokens=512,
+          do_sample=True,
+          temperature=0.1,
+          top_k=1,
+          top_p=1,
+          repetition_penalty=1.1
+      )[0]
+  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
+
+  results.append({"task_id": data["task_id"], "input": input, "output": output})
+```
+
+```python
+import re
+model_name = re.sub(".*/", "", model_name)
+with open(f"./{model_name}-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')
+```
+
 ## Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->