Enterprise SLM Platform
An open-source and no-code Small Language Model platform to create domain specific agents based on your personal and sensitive data saving cost and energy while maintaining high degree of accuracy
Platform features
Designed for private cloud and on-prem use cases tailored towards businesses and large organizations
Use the web UI to upload documents and then interact with them collectively via the assistant
Fully managed platform as a service
Energy and cost-efficient solution giving you the best value and performance
Run the fine-tuned model on device or behind a firewall
What we offer
Training and fine-tuning of your models
Pipeline to process, chunk and vectorize documents to extract information accurately
Cost-effective solution to tailored your needs
Uptime guarantee (99.5%)
Setting up on-prem or private cloud
Support and on-going improvements and updates
FAQ
01 What is an SLM?
01 What is an SLM?
A machine learning model that's based on a large language model (LLM), but is smaller and less complex. SLMs can be used for a variety of tasks, such as sentiment analysis, content generation, and data retrieve.
02 How much does it cost?
02 How much does it cost?
The free platform allows you to upload documents up to 5MB. We are working on an effective subscription plan that will allow you to upload larger documents and create your personalized assistant. If you require more storage or want to collaborate with us in training a custom model, please contact us at hello@smartloop.ai.
03 How do you train models?
03 How do you train models?
We use LoRA (Low Rank Adaption) to train models which makes it efficient in terms of memory, loading and un-loading of models. It happens behind the scene every time you upload a document from the UI. You can also use the Command-Line-Interface to download (coming soon) the compiled model (.gguf) and try it in your local machine.
04What is your base model?
04What is your base model?
We use 
Llama 3 as our base model that let us train and fine-tune the model as it fits. We are also big believers in open-source language model.
Use the power of Large Language Model in a small footprint, covering your static data into Agents to streamline your existing process and be more productive without compromising your privacy within your budget