Blogs

2024

• Part III: Fine-tuning Llama-3-8B for Structured Functional Representation Extraction
  July 15, 2024 — LLMs, Finetuning, Predibase, ViGGO, Llama, LORA
  In this blog post, I walk through the process of fine-tuning a Llama-3-8B model on the Predibase platform for structured functional representation extraction, and compare its performance with GPT-4 and Claude 3.5 Sonnet.

---

• Part II: Comparison of Model Performances on Structured Functional Representation Extraction
  July 09, 2024 — LLMs, GPT, Evaluation, ViGGO, Claude, Llama, Gemini, Mistral
  This blog post compares the performance of various models in extracting structured functional representations from text.

---

• Part I: Baseline Evaluation of GPT-4o for Functional Representation Extraction
  July 03, 2024 — LLMs, GPT, Evaluation, VIGGO
  In this blog, I walk you through structured data extraction, specifically functional representation, using OpenAI's GPT-4o model.

---

• Step-by-Step Guide to Setup Your Personal GPU Server
  June 30, 2024 — gpu, ngrok, openssh
  A concise guide to set up a remotely accessible personal GPU Ubuntu server, enabling its access from anywhere.

---

• Managing multiple CUDA versions using environment modules in Ubuntu
  May 19, 2024 — gpu, cuda, nvidia, module
  Guide to install CUDA locally and manage multiple cuda environments on Ubuntu GPU server.