Vibe Coding DiscoverCLM serves a contrastively trained model that scores candidate actions against a state, with an API for typed decisions and ranking. Use it for agent action selection, tool routing, or verifying and ranking generated solutions.
Use Cases
Rank candidate actions for an agentSelect tools based on current stateVerify and rank generated coding solutionsAnswer typed choice, score, and yes/no questionsClassify computer-use or game actionsRoute customer requests to departments
Built With
- Language
- Python
- Frameworks
- PyTorch · vLLM · FastAPI · Hugging Face
Tags
contrastive learning · state-action scoring · decision-making · model serving · verifier · tool selection · candidate ranking · embeddings · fine-tuning