Update README.md

README.md

@@ -2,6 +2,10 @@
 library_name: transformers
 datasets:
 - weblab-GENIAC/aya-ja-evol-instruct-calm3-dpo-masked
+language:
+- ja
+base_model:
+- llm-jp/llm-jp-3-13b
 ---
 
 # Model Card for Model ID
@@ -35,166 +39,122 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **Demo [optional]:** [More Information Needed]
 
 ## Uses
+実行の仕方は以下の通りです。 以下は、Model_Inference_Template_DPO_20241207.ipynbについて、モデルidのみを変えたものになっています。 omnicampus上での演習環境での使用を想定しています。
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+```
+!pip install -U ipywidgets
+!pip install transformers
+!pip install -U bitsandbytes
+!pip install -U accelerate
+!pip install -U datasets
+!pip install -U peft
+```
 
-### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+```python
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+)
+from peft import PeftModel
+import torch
+from tqdm import tqdm
+import json
 
-[More Information Needed]
 
-### Downstream Use [optional]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+# Hugging Faceで取得したTokenをこちらに貼る。
+HF_TOKEN = "your_token"
 
-[More Information Needed]
 
-### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-[More Information Needed]
+# ベースとなるモデルと学習したLoRAのアダプタ。
+# model_idの値はomnicampusの環境におけるモデルのパスを表しており、それ以外の環境で実行する場合は変更の必要があります。
+model_id = "models/models--llm-jp--llm-jp-3-13b/snapshots/cd3823f4c1fcbb0ad2e2af46036ab1b0ca13192a"
+# omnicampus以外の環境をご利用の方は以下をご利用ください。
+# base_model_id = "llm-jp/llm-jp-3-13b"
+adapter_id = "yuki-2000/llm-jp-3-13b-finetune1" # こちらにアップロードしたLoRAアダプタのHugging FaceのIDを指定してください。
+adapter_dpo_id = "yuki-2000/llm-jp-3-13b-finetune1-dpo1" # こちらにアップロードしたDPOアダプタのHugging FaceのIDを指定してください。
 
-## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-[More Information Needed]
 
-### Recommendations
+# QLoRA config
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+)
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
-## How to Get Started with the Model
 
-Use the code below to get started with the model.
 
-[More Information Needed]
+# Load model
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    quantization_config=bnb_config,
+    device_map="auto",
+    token = HF_TOKEN
+)
 
-## Training Details
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
 
-### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+# 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)
 
-[More Information Needed]
+# LoRAのモデルにDPOのアダプタを統合。
+model = PeftModel.from_pretrained(model, adapter_dpo_id, token = HF_TOKEN)
 
-### Training Procedure
+# データセットの読み込み。
+# omnicampusの開発環境では、左にタスクのjsonlをドラッグアンドドロップしてから実行。
+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 = ""
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+# llmjp
+results = []
+for data in tqdm(datasets):
 
-#### Preprocessing [optional]
+  input = data["input"]
 
-[More Information Needed]
+  prompt = f"""### 指示
+  {input}
+  ### 回答
+  """
 
+  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
+  attention_mask = torch.ones_like(tokenized_input)
+  with torch.no_grad():
+      outputs = model.generate(
+          tokenized_input,
+          attention_mask=attention_mask,
+          max_new_tokens=100,
+          do_sample=False,
+          repetition_penalty=1.2,
+          pad_token_id=tokenizer.eos_token_id
+      )[0]
+  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
 
-#### Training Hyperparameters
+  results.append({"task_id": data["task_id"], "input": input, "output": output})
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+# こちらで生成されたjsolを提出してください。
+# 本コードではinputも含んでいますが、なくても問題ありません。
+# 必須なのはtask_idとoutputとなります。
+import re
+jsonl_id = re.sub(".*/", "", adapter_dpo_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')
+```