• Add a new serverless configuration in Promptitude: In Promptitude, go to Settings > Serverless and click the New Inference button at the bottom right. Available for Enterprise Plans.
• In the slide-over, choose your cloud provider and name the connection (just use the provider name for starters).
• Click Save, and you're ready to configure your provider and deploy your models.

➔ Follow step by step and find out the requirements for each cloud provider.

Users can leverage Hugging Face by accessing its open-source library, uploading or selecting pre-trained models, fine-tuning them for specific tasks, and deploying them using the Inference API or hosting options.

‍

‍Hugging Face: Integrate your AI models seamlessly.

• How to get your model ID and access token
• How to obtain your Inference Model Endpoint URL and Access Token

Use cases

• Text Classification: Using models like BERT for sentiment analysis and sentence classification.
• Language Translation: Utilizing models such as T5 for multilingual applications.
• Content Creation: Leveraging GPT for generating human-like text in blog posts, articles, and marketing content.
• Multimodal Applications: Employing CLIP for image classification and understanding visual content.
• Multilingual Tasks: Using BLOOM for creating content and retrieving information across different languages.