Update README.md

README.md

@@ -37,6 +37,81 @@ And then fine-tuned using LoRA with dataset:
 - h: kanhatakeyama/ramdom-to-fixed-multiturn-Calm3
 - a: Aratako/Magpie-Tanuki-8B-97k
 
+## Use for Evaluation
+
+```python
+# -*- coding: utf-8 -*-
+
+!pip install -U bitsandbytes
+!pip install -U transformers
+!pip install -U accelerate
+!pip install -U datasets
+!pip install -U peft
+
+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 = "dummy"
+
+model_id = "niryuu/llm-jp-3-13b-ha"
+
+# 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)
+
+# load dataset
+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 = ""
+
+results = []
+for data in tqdm(datasets):
+
+  input = data["input"]
+  token_ids = tokenizer.apply_chat_template([{"role": "user", "content": input}], tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
+
+  outputs = model.generate(input_ids, max_new_tokens=2048, do_sample=False, repetition_penalty=1.2,)
+  output = tokenizer.decode(outputs[0][token_ids.size(1) :], skip_special_tokens=True)
+
+  results.append({"task_id": data["task_id"], "input": input, "output": output})
+
+# save outputs
+import re
+jsonl_id = re.sub(".*/", "", model_id)
+with open(f"./{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')
+```
+
 ## Use with mlx
 
 ```bash