Update README.md

README.md

@@ -6,17 +6,105 @@ tags:
 - unsloth
 - llama
 - trl
-license: apache-2.0
+license: cc
 language:
 - en
+datasets:
+- weblab-GENIAC/aya-ja-nemotron-dpo-masked
 ---
 
 # Uploaded  model
 
 - **Developed by:** thesugar
-- **License:** apache-2.0
+- **License:** CC-BY-NC-SA  
 - **Finetuned from model :** llm-jp/llm-jp-3-13b
 
 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)
+
+# HOW TO INFERENCE for competition evaluators
+
+Google Colab L4 で実行
+
+```ipynb
+!pip install unsloth
+!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir --no-deps git+https://github.com/unslothai/unsloth.git
+
+HF_TOKEN = # WRITE YOUR HF_TOKEN
+ELYZA_TASKS_100_TV_JSONL_PATH = # WRITE
+# Output for elyza-tasks-100-tv is saved as "output.jsonl"
+
+
+from huggingface_hub import login
+login(HF_TOKEN)
+
+from unsloth import FastLanguageModel
+import torch
+
+max_seq_length = 2048
+dtype = torch.bfloat16
+load_in_4bit = True
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "thesugar/llm-jp-3-13b-it_lora-DPO-12-16",
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    token = HF_TOKEN,
+)
+
+import json
+datasets = []
+with open(ELYZA_TASKS_100_TV_JSONL_PATH, "r") as f:
+    item = ""
+    for line in f:
+      line = line.strip()
+      item += line
+      if item.endswith("}"):
+        datasets.append(json.loads(item))
+        item = ""
+
+from tqdm import tqdm
+
+FastLanguageModel.for_inference(model)
+model.eval()
+
+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 = 2048, 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})
+
+with open("output.jsonl", "w") as f:
+  for r in results:
+    f.write(json.dumps(r, ensure_ascii=False) + "\n")
+```
+
+# Development steps
+- `llm-jp/llm-jp-3-13b` を量子化
+- インストラクションチューニング
+  - `ichikara-instruction` データセットの `ichikara-instruction-003-001-1.json`, `ichikara-instruction-003-002-1.json` の全データを使用
+- direct policy optimization
+  - `weblab-GENIAC/aya-ja-nemotron-dpo-masked` からランダムに選択した 100 レコードを使用
+
+# Used datasets　and their licenses
+## ichikara-instruction: LLMのための日本語インストラクションデータ
+- [LLMのための日本語インストラクションデータ 公開ページ – LIAT-AIP homepage](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/)
+
+関根聡, 安藤まや, 後藤美知子, 鈴木久美, 河原大輔, 井之上直也, 乾健太郎. ichikara-instruction: LLMのための日本語インストラクションデータの構築. 言語処理学会第30回年次大会(2024)
+CC-BY-NC-SA  
+
+## weblab-GENIAC/aya-ja-nemotron-dpo-masked
+- [creator](https://huggingface.co/weblab-GENIAC)
+- [repository](https://huggingface.co/datasets/weblab-GENIAC/aya-ja-nemotron-dpo-masked)
+
+weblab-GENIAC  
+weblab-GENIAC/aya-ja-nemotron-dpo-masked  
+Apache License 2.0