hiroki-rad
/

llm-jp-llm-jp-3-13b-16-ft

@@ -1,199 +1,117 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[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 -->
-[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]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- 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]
-## Training Details
-### 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. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **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]

 ---
 library_name: transformers
+datasets:
+- elyza/ELYZA-tasks-100
+language:
+- ja
+base_model:
+- llm-jp/llm-jp-3-13b
+pipeline_tag: text-generation
 ---
+## How to Uses
+```python
+# ライブラリのインストール
+!pip install -U langchain-community langchain-huggingface vllm triton fugashi unidic-lite
+# インストール
+import json
+import pandas as pd
+from tqdm import tqdm
+from transformers import pipeline
+from langchain_community.llms import VLLM
+from langchain.prompts import PromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain.schema.output_parser import StrOutputParser
+# GitHub repositoryのclone
+!git clone https://github.com/y-hiroki-radiotech/llm-final-task.git
+%cd llm-final-task
+# タスク別に設定したプロンプトを使うために、PromptStockクラスをインスタンス化
+from prompt import PromptStock
+prompt_stock = PromptStock()
+# データのpandas形式で準備する
+file_path = 'elyza-tasks-100-TV_0.jsonl' # ここにjsonlを指定する
+data = pd.read_json(file_path, lines=True)
+# データのinputに対して、タスクラベルを与える。タスクを8分類してある。
+model_name = "hiroki-rad/bert-base-classification-ft"
+classify_pipe = pipeline(model=model_name, device="cuda:0")
+results: list[dict[str, float | str]] = []
+for example in data.itertuples():
+    # モデルの予測結果を取得
+    model_prediction = classify_pipe(example.input)[0]
+    # 正解のラベルIDをラベル名に変換
+    results.append( model_prediction["label"])
+data["label"] = results
+# タスク回答のためのモデルをvLLMを使ってインストール
+model_name = "hiroki-rad/llm-jp-llm-jp-3-13b-16-ft"
+llm = VLLM(model=model_name,
+           quantization="awq")
+# テンプレートの作成
+template = """
+ユーザー: 質問を良く読んで、適切な回答をしてください。
+{context}
+質問:{input}
+回答:"""
+prompt = PromptTemplate(
+    template=template,
+    input_variables=["context", "input"],
+    template_format="f-string"
+)
+# chainの作成
+vllm_chain = prompt | llm
+chain = (
+    RunnablePassthrough()
+    | vllm_chain
+    | StrOutputParser()
+)
+outputs = []
+total_rows = len(data)
+with tqdm(total=total_rows,
+          desc="Processing rows",
+          position=0,
+          leave=True
+         ) as pbar:
+    for row in data.itertuples():
+        prompt_string = prompt_stock.get_prompt(row.label)
+        input_dict = {
+            "context": prompt_string,
+            "input": row.input
+        }
+        output = chain.invoke(input_dict)
+        outputs.append(output)
+        pbar.update(1)
+# 出力
+jsonl_data = []
+for i in range(len(data)):
+    task_id = data.iloc[i]["task_id"]
+    output = outputs[i]
+    jsonl_object = {
+        "task_id": task_id,
+        "output": output
+    }
+    jsonl_data.append(jsonl_object)
+with open("output.jsonl", "w") as outfile:
+  for entry in jsonl_data:
+    entry["task_id"] = int(entry["task_id"])
+    json.dump(entry, outfile)
+    outfile.write('\n')