Foundation Model Evaluator
Dive into the Stellantis Foundation Model Challenge and shape the future of AI. Develop an innovative concept or prototype to assess & evaluate the performance of foundation models, optimizing their selection process for practical AI use cases. This is your chance to demonstrate your expertise and potentially secure Stellantis as a big partner in GenAI innovation.
Who can participate?
Open to startups, tech companies, researchers, and AI innovators with a knack for advancing the practical use of GenAI.
#GenAI #FoundationModels #ModelEvaluation
✅ Completed 🏁 Winner JadenDate & Patronus AI
🏆 Prize Funded co-creation, strategic partnerships & long-term integration
🌎 Scope Global
❓Questions Feel free to join our Q&A Calls
👥 Looking for a team? Join our Team Matching Channel
In this tab you will find more information on foundation model use cases.
Current foundation model use cases
At Stellantis, the application of Generative AI currently focuses on enhancing text-based tasks to streamline internal workflows and improve information processing.
- 80 percent of the projects now focus on specific text generation and data processing use cases.
- Projects in play, mostly utilize sophisticated models like GPT-4, but there's a push to find more cost-effective and at least equally capable alternatives.
Following you can find a list of current use case types for a better understanding:
- Chatbot: chatbot interface with RAG engine backend to "talk to documents" (engineering standards e.g.).
- Verbatim classification: LLM to classify verbatims. Can be sentiment analysis, defect categorization, etc.
- Summarization: summarization of documents, translate text or classify text.
- Video generation: content generation for learning.
- Image classification: manufacturing defect detection.