solbi12
/

ecommers_fasion_fine_tuned_3class_model

@@ -1,199 +1,180 @@
 ---
 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]

 ---
+pipeline_tag: text-classification
+tags:
+  - sentiment-analysis
+  - text-classification
+  - korean
+  - ecommerce
+  - fashion
 library_name: transformers
+license: apache-2.0
+language:
+  - ko
+widget:
+  - text: "배송이 빠르고 품질도 좋아요"
+  - text: "원단이 얇고 마감이 별로네요"
+  - text: "가격은 괜찮은데 디자인이 마음에 안 들어요"
+model-index:
+  - name: eCommerce Fashion 3-class (KoELECTRA)
+    results:
+      - task:
+          type: text-classification
+          name: Sentiment Analysis
+        dataset:
+          name: Custom Fashion Reviews (ko)
+          type: custom
+        metrics:
+          - name: Accuracy
+            type: accuracy
+            value: 0.91
+          - name: F1 (weighted)
+            type: f1
+            value: 0.90
 ---
+# 🛍️ eCommerce Fashion 한국어 감정분석 (3-Class)
+[![Transformers](https://img.shields.io/badge/HF-Transformers-blue?logo=huggingface)](https://huggingface.co/solbi12/ecommers_fasion_fine_tuned_3class_model)
+![License](https://img.shields.io/badge/License-Apache%202.0-green)
+![Lang](https://img.shields.io/badge/Language-Korean-orange)
+![Task](https://img.shields.io/badge/Task-Sentiment%20Analysis-purple)
+한국어 **패션 리뷰** 도메인에 특화된 **3-클래스 감정분석 모델**입니다.
+`KoELECTRA-base`를 기반으로 파인튜닝 했으며, 라벨은 **NEGATIVE(0) / NEUTRAL(1) / POSITIVE(2)** 입니다.
+---
+## ✨ 특징
+- 한국어 패션 리뷰(배송/품질/디자인 등)에 최적화
+- 부정/중립/긍정 **3-class 분류**
+- Hugging Face Inference Widget 및 Transformers 라이브러리로 즉시 사용 가능
+---
+## 🚀 사용법
+### 👉 파이프라인
+```python
+from transformers import pipeline
+repo_id = "solbi12/ecommers_fasion_fine_tuned_3class_model"
+clf = pipeline("text-classification", model=repo_id, truncation=True)
+clf("배송이 빠르고 품질도 좋아요")
+# [{'label': 'POSITIVE', 'score': 0.98}]
+---
+## 📜 README.md (마크다운 형식)
+### 💻 모델 사용 방법: PyTorch 직접 사용
+이 모델은 한국어 패션 리뷰의 감정을 긍정(POSITIVE), 부정(NEGATIVE), 중립(NEUTRAL) 3가지로 분류하도록 파인튜닝되었습니다. `transformers` 라이브러리를 사용하여 쉽게 로드하고 추론할 수 있습니다.
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+# 모델 ID
+repo_id = "solbi12/ecommers_fasion_fine_tuned_3class_model"
+# 모델 및 토크나이저 로드 (Hugging Face Hub에서 자동 다운로드)
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForSequenceClassification.from_pretrained(repo_id).eval()
+# 테스트 텍스트
+text = "원단이 얇고 마감이 별로네요"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+# 추론
+with torch.no_grad():
+    logits = model(**inputs).logits
+    pred = int(logits.argmax(dim=-1))
+# 라벨 출력
+label_map = {0: "NEGATIVE", 1: "NEUTRAL", 2: "POSITIVE"}
+print(f"입력 텍스트: '{text}'")
+print(f"분류 결과: {label_map[pred]}")
+```
+-----
+### 🏷️ 라벨 정의
+| 라벨 ID | 라벨명 |
+| :--- | :--- |
+| **0** | **NEGATIVE** (부정) |
+| **1** | **NEUTRAL** (중립) |
+| **2** | **POSITIVE** (긍정) |
+> `id2label` 및 `label2id`가 모델 설정(`config.json`)에 저장되어 있어 Hugging Face `pipeline` 사용 시에도 라벨명이 자동으로 출력됩니다.
+-----
+### 📊 성능 (Validation Set 기준)
+| 지표 | 점수 |
+| :--- | :--- |
+| Accuracy | **0.91** |
+| F1-score | **0.90** |
+> **데이터**: 사내/커스텀 한국어 패션 리뷰 데이터셋
+-----
+### 🏗️ 학습 정보
+  - **Base Model**: `jaehyeong/koelectra-base-v3-generalized-sentiment-analysis`
+  - **최대 입력 길이**: 512 토큰
+  - **배치 크기**: 32
+  - **에포크**: 5
+  - **학습률**: 2e-5 (`warmup` 10%)
+  - **옵티마이저**: AdamW (`weight decay` 0.01)
+  - **손실 함수**: 가중치 부여 교차 엔트로피 (`Weighted CrossEntropy`)
+-----
+### 📦 파일 구성
+  - `config.json` : 모델 구조 및 학습 설정
+  - `model.safetensors` : 파인튜닝된 모델 가중치
+  - 토크나이저 파일들 :
+      - `tokenizer.json`
+      - `tokenizer_config.json`
+      - `vocab.txt`
+      - `special_tokens_map.json`
+-----
+### ⚠️ 한계와 주의 사항
+  - **도메인 특화**: 이 모델은 **패션 리뷰 도메인에 최적화**되어 학습되었습니다. 다른 도메인(예: IT 기기, 영화 리뷰)의 텍스트에 대해서는 성능이 저하될 수 있습니다.
+  - **입력 길이 제한**: 입력 텍스트가 512 토큰을 초과할 경우, 초과된 부분은 **자동으로 잘립니다(truncation)**.
+  - **컨텍스트 부재**: 이 모델은 텍스트 자체만을 분석하며, 리뷰에 첨부된 상품 이미지, 가격, 사용자 평점 등의 **외부 컨텍스트는 고려하지 않습니다.**
+-----
+### 🔒 라이선스
+  - **라이선스**: Apache-2.0
+  - **면책 조항**: 모델 사용 시 **데이터 및 도메인 적합성**은 사용자 본인의 책임입니다.
+-----
+### 🙌 인용 (Citation)
+본 모델을 학술적 또는 상업적 목적으로 사용할 경우, 아래와 같이 인용해 주세요.
+```
+@article{lee2025ecommers,
+  title={eCommerce Fashion Korean Sentiment (3-Class)},
+  author={Lee, Solbi},
+  year={2025},
+  note={https://huggingface.co/solbi12/ecommers_fasion_fine_tuned_3class_model}
+}
+```
+또는 일반적인 텍스트 형식으로:
+**Solbi Lee, eCommerce Fashion Korean Sentiment (3-Class), 2025.**
+**모델 링크:** [https://huggingface.co/solbi12/ecommers\_fasion\_fine\_tuned\_3class\_model](https://huggingface.co/solbi12/ecommers_fasion_fine_tuned_3class_model)