LLM Fine-Tuning & Local Inference

Fine-tuning open-source LLMs with LoRA and running them locally via Ollama and llama.cpp.

NLPDeep Learning
datalanguagemodelnlptokenstextvectorvocab

Overview

Personal exploration of parameter-efficient fine-tuning for open-source LLMs (LoRA), with local inference via Ollama and llama.cpp. Includes prompt-engineering experiments and adapter-merging for domain-specific tasks.

Key Highlights

  • LoRA fine-tuning for domain-specific tasks
  • Local inference via Ollama and llama.cpp
  • Prompt-engineering and adapter merging experiments

Tech Stack

PythonPyTorchPEFTTransformersOllama

Other Projects

All Projects

Stay Updated

Subscribe to get the latest blog posts, project updates, and data science insights straight to your inbox.

No spam. Unsubscribe anytime.