+
Skip to content
View en-jai-neer's full-sized avatar
1 follower · 3 following

Highlights

  • Pro

Block or report en-jai-neer

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
en-jai-neer/README.md

Hi there 👋 I'm Jai

🔬 I'm currently working on

  • ⚡ Efficient LLMs: Faster Inference using LoRA, distillation, quantization, KV cache compression
  • 🤖 AI Agents: Natural language-driven task automation using LLMs
  • 📚 RAG Systems: QA bots grounded in reliable, structured data

🛠️ Projects

  • ⚙️ QaLoF — Switchable + dynamic quantization with LoRA finetuning for efficient GPT-2
  • 🔎 Browser Agent — Natural language to web automation using LLMs
  • 🎓 GT Chatbot — LLM for GT students that uses RAG to better answer scheduling and academic queries.

⚙️ Skills

Python · PyTorch · Transformers · LangChain · AI Agents · AWS · LoRA · RAG · Prompt Engineering · Playwright

Open to collaborations on applied ML, LLM systems, and agent-based architectures.

Pinned Loading

  1. QaLoF QaLoF Public

    QaLoF (Quantization-Aware LoRA Finetuning) with per-layer bit-width control, cyclic precision training, and adversarial robustness for GPT-2 models

    Python 1

  2. browser_automation_ai_agent browser_automation_ai_agent Public

    An intelligent browser AI agent that automates tasks given in natural language

    Python

  3. reggie-gt-chatbot reggie-gt-chatbot Public

    🤖 Reggie - A GPT+RAG powered registration assistant for Georgia Tech students. Features real-time course availability, professor ratings, Canvas integration, syllabus analysis, and degree planning …

    Python

  4. kv-cache-compression kv-cache-compression Public

    Efficient KV-cache compression for Large Language Models using pyramidal layer-aware merging and token pooling strategies.

    Python

  5. nirbhar-udp nirbhar-udp Public

    Reliable UDP implementation with Selective Repeat ARQ for guaranteed file transfer over unreliable networks with comprehensive performance testing

    Python

  6. queue-as-a-service queue-as-a-service Public

    My implementation of a RESTful message queue service built with Java and PostgreSQL, offering simple APIs for sending, peeking, and removing messages

    Java 1

点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载