Update README.md

README.md

@@ -11,23 +11,73 @@ language:
 - en
 ---
 
-# How to Run thie Model
+# How to Run this Model
 基本的にhugging face modelとしてloadすればOK。
+** elyza-tasks-100-TV_0.jsonl を事前に同じフォルダーに置いてください。 **
+
+
+環境準備
+
+```
+!pip install -U bitsandbytes
+!pip install -U transformers
+!pip install -U accelerate
+!pip install -U datasets
+```
+
+
+
 コード例
 ```
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+)
+import torch
+from tqdm import tqdm
+import json
+
+HF_TOKEN = "hf_ddlNeFZWWURoIBcXhAlVIxAYErhqLntJjYn"
+model_name = "AlHfac/llm-jp-3-13b-it"
+
+# QLoRA config
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_quant_type="nf4",
     bnb_4bit_compute_dtype=torch.bfloat16,
     bnb_4bit_use_double_quant=False,
 )
+# Load model
 model = AutoModelForCausalLM.from_pretrained(
-    'AlHfac/llm-jp-3-13b-it',
+    model_name,
     quantization_config=bnb_config,
     device_map="auto",
     token = HF_TOKEN
 )
-tokenizer = AutoTokenizer.from_pretrained('AlHfac/llm-jp-3-13b-it', trust_remote_code=True, token = HF_TOKEN)
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, token = HF_TOKEN)
+
+# Evaluate
+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 = ""
+
+# Generate jsonl
+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')
+
 ```
 
 # Model Training Information