www.ai.rs

community
Verified
Activity Feed

AI & ML interests

- Natural Language Processing - Text Generation - Conversational AI - Fine-tuning - Retrieval-Augmented Generation - Reinforcement Learning from Human Feedback - Quantization - E-Commerce - Recommendation Systems - Edge AI

Organization Card

title: README
emoji: ๐Ÿค–
colorFrom: blue
colorTo: cyan sdk: static
pinned: false

๐Ÿค– ai.rs โ€” Custom AI for E-Commerce

We build AI sales assistants for e-commerce businesses. Our models know your products, speak your brand, and work 24/7.

๐Ÿ”ง What We Build

  • ๐Ÿง  Fine-tuned LLMs โ€” Custom-trained Qwen, Llama, and Mistral models on your product catalog
  • ๐Ÿ” RAG Pipelines โ€” Real-time retrieval from your database for accurate pricing, availability, and specs
  • ๐Ÿ’ฌ AI Sales Assistants โ€” Embedded chat that recommends products, answers questions, and drives conversions
  • ๐Ÿ–ฅ Dedicated Deployment โ€” Your own server, your own data, no shared infrastructure

โš™ Our Approach

  1. Data preparation โ€” We structure your product catalog, FAQs, and sales conversations into training data (~26,000+ examples per deployment)
  2. Fine-tuning โ€” We train on open-source base models (Qwen 2.5, Llama 3, Mistral) using your domain-specific data
  3. Safety training โ€” DPO alignment to keep responses on-brand and prevent hallucination
  4. RAG integration โ€” Vector search + live database queries for real-time pricing and inventory
  5. Deployment โ€” Dedicated GPU server running vLLM, with monitoring and updates

๐Ÿ›  Tech Stack

Component Technology
Base models Qwen 2.5 (8B), Llama 3 (8B), Mistral (7B)
Fine-tuning LoRA / QLoRA, custom training pipelines
Serving vLLM on dedicated GPU servers
RAG Vector embeddings + live SQL/API queries
Infrastructure Rust + Python

๐Ÿ“ Based in Belgrade, Serbia

Serving e-commerce businesses across Europe and beyond.

๐ŸŒ ai.rs ยท ๐Ÿ“ง github@ai.rs ยท ๐Ÿ™ GitHub

models 0

None public yet

datasets 0

None public yet