InternshipTools and first-week setup
The tools a LLM Engineering & Fine-Tuning intern uses and how to set up your workspace in week one.
These are the main tools for LLM Engineering & Fine-Tuning tasks. You do not need all of them on day one; the Level 1 tasks tell you when to install each one.
- Python
- Hugging Face Transformers & PEFT
- Ollama / llama.cpp
- Chroma / pgvector
- Gemini, Groq or other LLM APIs
- Google Colab / Kaggle GPUs
- FastAPI
Set up your workspace
- Create a free GitHub account if you do not have one, with a professional username, and set up your LinkedIn profile: every task is submitted with a LinkedIn post.
- Create one repository for the internship, for example llm-engineering-and-fine-tuning-internship, with a README that says who you are and what the repo holds.
- Keep one folder per task, named with the task number and title, so mentors find your work quickly.
- Commit small changes every day with clear messages. Your daily work report uses these commits as proof.
- Never commit passwords, API keys or personal data. Put secrets in a .env file and add it to .gitignore.
Your first tasks
| Task | What to do |
|---|---|
| How LLMs work | In a README in a repo named llm-internship, explain tokens, the context window, next-token prediction, temperature and hallucination with your own small examples. |
| Count tokens | Use a tokenizer library (tiktoken or a Hugging Face tokenizer) to count tokens for 5 sentences in English and 2 in Tamil or Hindi. Note why the counts differ. |
| First API call from Python | Call any LLM API (Gemini free tier, Groq or a local Ollama model) from a Python script. Keep the API key in a .env file that is listed in .gitignore. |
| Run a model on your laptop | Install Ollama, run a small open model (such as Llama 3.2 3B or Qwen 2.5 3B) and record the answer speed in tokens per second. |