SoyunKim
/

StartBridge

@@ -1,200 +1,73 @@
----
-library_name: transformers
-tags:
-- unsloth
----
 # 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
+tags:
+- unsloth
+license: gemma
+datasets:
+- SoyunKim/startrup
+language:
+- ko
+base_model:
+- google/gemma-2-2b
+---
 # Model Card for Model ID
+**StartBridge** is a machine learning model that helps startups find relevant 2024 government startup support programs by providing quick, personalized answers about funding and opportunities.
 ## Model Details
+Introducing **StartBridge**, your go-to guide for navigating 2024 government support programs for startups! Designed with fine-tuning machine learning, **StartBridge** bridges the gap between you and the vast world of public funding, making it easier than ever to find the right opportunities.
+Whether you’re an entrepreneur searching for startup grants or a business in need of early-stage funding, **StartBridge** swiftly delivers clear, relevant, and personalized answers to your questions. With **StartBridge**, no more sifting through countless websites or documents—simply ask, and get connected to the right support in seconds. It's not just a tool, it's your personal bridge to growth and innovation!
+### Model Description
+  - **Developed by:** Soyun Kim, Su-min Kim
+  - **Activity with:** MLB 2024, Gemma Sprint
+  - **Model type:** Causal Language Model (AutoModelForCausalLM)
+  - **Language(s) (NLP):** Korean
+  - **License:** Gemma Term of Use
+  - **Finetuned from model:** google/gemma2-2b
+**Model Sources**
+  - **Reference #1:** https://github.com/unslothai/unsloth.git
+  - **Reference #2:** https://www.sktenterprise.com/bizInsight/blogDetail/dev/9480
+  - **Reference #3:** https://unfinishedgod.netlify.app/2024/06/15/llm-unsloth-gguf/
+**Data Resource**
+  - **Resource**: https://huggingface.co/datasets/SoyunKim/startrup
 ## 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. -->
+1. **Intended Use**:
+  - **StartBridge** is designed to help users find relevant government support programs specifically targeted towards startups. It serves as a query-based system where users can ask questions about available programs, eligibility criteria, deadlines, application processes, and any other relevant details.
+  - The model can provide information by matching user queries with existing data about various support programs, simplifying the process for startups seeking government assistance.
+2. **Foreseeable Users**:
+  - **Startups and Entrepreneurs**: The primary users of the model will be founders, entrepreneurs, or teams looking to access government grants, subsidies, tax reliefs, or any other form of financial or administrative support.
+  - **Business Advisors and Consultants**: Professionals who assist startups in navigating the complex landscape of government support programs may use the model to provide quick and accurate answers to their clients.
+  - **Incubators and Accelerators**: Organizations that provide mentorship and resources to early-stage startups may also use the model to assist their cohorts in understanding available government programs.
+3. **Those Affected by the Model**:
+  - **Entrepreneurs**: With better access to information, entrepreneurs may have a more equitable chance of benefiting from the support programs, potentially influencing startup growth rates and success rates.
+  - **Policymakers**: Insights from the types of questions users ask can help policymakers refine or promote certain programs, ensuring that they meet the needs of startups more effectively.
 ## Bias, Risks, and Limitations
 <!-- This section is meant to convey both technical and sociotechnical limitations. -->
+1. **Bias**:
+  - **StartBridge** has been primarily trained on data from **2024 government startup support programs** focusing specifically on **commercialization support** (사업화지원). This creates a potential bias, as the model's responses will be most accurate for questions related to this area.
+  - Programs supporting other aspects of startups, such as funding for research and development (R&D), international expansion, or human resources, may not be covered as thoroughly, leading to gaps in the information provided.
+  - The list of programs currently covered is as follows:
+  민관공동창업자발굴육성사업, 예비창업패키지, 초기창업패키지, 창업도약패키지, 초격차 스타트업 1000+ 프로젝트, 아기유니콘 육성사업, 재도전성공패키지, 창업중심대학, 생애최초 청년창업 지원사업, 공공기술 창업사업화 지원사업, 창업성공패키지(청년창업사관학교), 로컬크리에이터 육성사업, K-Global 액셀러레이터 육성사업, 글로벌 ICT 미래 유니콘 육성, 데이터 활용 사업화 지원사업(DATA-Stars), 에코스타트업 지원사업, 대한민국 물산업 혁신창업 대전, 물드림 사업화지원, 예술기업 성장 지원, 스포츠산업 창업 지원, 스포츠산업 창업중기(액셀러레이팅) 지원, 콘텐츠 아이디어 사업화 지원, 콘텐츠 초기창업 육성 지원, 콘텐츠 창업도약 프로그램, 선도기업 연계 동반성장 지원(콘텐츠 오픈이노베이션), 전통문화 청년창업 육성지원사업, 관광벤처사업 공모전, 관광 액셀러레이팅 프로그램, 신사업창업사관학교, 농식품 벤처육성지원, 농식품 기술창업 액셀러레이터 육성지원, 농식품 기술평가지원, 농식품 판로지원, 유망 창업기업 투자유치 지원사업
+2. **Risks**:
+  - **Outdated Information**: Since the model is trained on a specific dataset from 2024, there is a risk that it may provide outdated or incomplete information if not updated regularly, especially as new government programs or changes to existing programs emerge.
+  - **Over-reliance on the Model**: Users may rely solely on the model without verifying the information through official channels, potentially leading to missed opportunities or misunderstandings in program eligibility and application requirements.
+  - **Limited Context**: The model might lack the ability to fully understand complex or nuanced queries that require knowledge beyond the provided dataset, which could result in incorrect or incomplete responses.
+3. **Limitations**:
+  - **Data Scope**: As of now, **StartBridge** is trained only on data related to **commercialization support programs** in 2024. This limits the model’s effectiveness when users ask about other areas of startup support such as tax incentives, infrastructure support, or legal assistance.
+  - **Language and Terminology Variations**: If users use different terms or phrases that aren't covered in the dataset, the model may struggle to interpret the question correctly.
+  - **Future Updates**: The model is expected to be updated continuously as more data on new government programs and support areas become available. While this will expand its scope, users must be aware that the current version is limited in coverage.