Update README.md

README.md

@@ -9,6 +9,7 @@ tags:
 license: apache-2.0
 language:
 - en
+- ja
 ---
 
 # Uploaded  model
@@ -20,3 +21,88 @@ language:
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+
+## 学習データ
+
+使用したSupervised fien-tune用dataset：下記からランダムに20000データを抽出  
+DeL-TaiseiOzaki/Tengentoppa-sft-v1.0    
+🌾 ランダムに20000データを取り出して学習
+
+SFTに用いた継続事前学習モデル
+ikedachin/llm-jp-3-13b-october-news-e1-all-3-5
+
+
+
+### 実行コード
+
+```:Python
+# import libraries
+import re
+import json
+
+import torch
+
+from peft import PeftModel
+from tqdm import tqdm
+from unsloth import FastLanguageModel
+
+# define base model_id and peft model_id
+model_id = "llm-jp/llm-jp-3-13b"
+adapter_id = "ikedachin/llm-jp-3-13b-october-news-e1-all-3-5-sft-ozaki-30000"
+
+dtype = None
+load_in_4bit
+
+# down load base model
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name=model_id,
+    dtype=dtype,
+    load_in_4bit=load_in_4bit,
+    trust_remote_code=True,
+)
+
+# adapt peft model
+model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
+
+
+# prepare dataset elyza-tasks-100-TV_0.jsonl
+datasets_elyza = []
+
+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_elyza.append(json.loads(item))
+            item = ""
+
+
+# change mode for inference
+FastLanguageModel.for_inference(model)
+
+# inferrence
+results = []
+
+for dt in tqdm(datasets):
+    input = dt["input"]
+
+    prompt = f"""### 指示\n{input}\n### 回答\n"""
+
+    inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
+
+    outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2)
+    prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
+
+    results.append({"task_id": dt["task_id"], "input": input, "output": prediction})
+
+# create result file as jsonl type
+json_file_id = re.sub(".*/", adapter_id)
+with open(f"/content/{json_file_id}_output.jsonl", 'w', encoding='utf-8') as f:
+    for result in results:
+        json.dump(result, f, ensure_ascii=False)
+        f.write('\n')
+
+
+```