# Overview — M.E.F LLM Studio

Source: https://www.mef-llm-studio.com/en/

Understand language models. By building one yourself.

M.E.F LLM Studio is an educational app for beginners: understand language models through clear explanations and small, hands-on experiments, without writing scripts. Follow the path from tokens through training to generated text. Brain Explorer, Wiki and Vision also make text and image generation explorable step by step.

From an explanation to your own experiment.

Read what a tokenizer does, then inspect your own text. Learn what loss means, then follow a training run. The learning overview connects the fundamentals with practical tools, turning terminology into relationships you can observe.

## 01. Understand a question

Read the relevant chapter: What are tokens? How does a model learn? What does a loss curve tell you?

## 02. Run your own experiment

Work with a short text or a small model. Change one setting deliberately and observe what happens.

## 03. Interpret the result

Compare your observation with the explanation. Even nonsensical output is a reason to examine the data, training and limitations more closely.

The first version is for non-commercial evaluation. Features may change and training may fail. Back up your data and do not use the alpha in production.

Inspired by [Language Model Builder](https://languagemodelbuilder.com/) by Felix Rieseberg.

## Understand what your model does.

Go beyond training a model. Explore how it processes text and compare its predictions across saved training checkpoints.

### Explore step by step

Follow tokens through embeddings, attention and output. The learning lab explains the steps of a recorded pass and shows how temperature and filters change selection probabilities.

### Compare training checkpoints

Compare checkpoints using the same prompt. Recorded-candidate ranks, difference bars and a manual A/B view reveal changes in next-token predictions. Export the comparison table as CSV.

### Train with examples

Move from pre-training to fine-tuning: SFT learns from example replies, DPO from preferred and rejected replies, and ORPO combines response tuning with a preference signal. Download offered datasets or edit your own examples in dedicated editors.

### Keep track of checkpoints

Manage and rename saved checkpoints, inspect their recorded history and Best markers, resume a run with its loss history, or open a state directly in Sampling or Chat.

### Link local models and compare answers

Link a supported Llama or Qwen2 Safetensors folder without copying its weights. Choose CPU, NVIDIA GPU or A/B and check memory before loading.

### Continue after a restart

Inputs, chat history and fine-tuning drafts are restored locally. They are stored unencrypted in the app-data area and can be cleared in Settings.

### Plan GPU and memory use

Review estimated training VRAM or a linked model’s RAM/VRAM plan before starting. Available runtime measurements remain separate from estimates.

Ranks and probabilities refer to the recorded candidates. “Best” is a historical marker, not a quality rating. Memory figures are estimates. External execution supports Llama/Qwen2 text models without quantization, custom code or multimodality. A/B does not judge either answer; texts are saved only when you choose to.

## New in 0.2.0: From a concept to a visible computation.

Alpha 0.2.0 extends the learning path with Brain Explorer, Wiki and Vision: understand concepts, run your own experiments and inspect the computation step by step.

### Brain Explorer

How is a reply built, token by token?

A 2D view connects context, transformer blocks, probabilities and sampling. Play a recording, pause it or inspect each step individually.

### Wiki & Explain

What does the term on this screen mean?

Learning chapters and a searchable Wiki connect fundamentals to experiments. Explain mode describes highlighted terms beside the visible interface.

### Vision & Vision Explorer

How does noise become an image?

Generate images locally with a supported model and open the recording directly in the Vision Explorer. Follow denoising step by step: state before, noise prediction and state after.

[See the changes in 0.2.0](https://www.mef-llm-studio.com/en/changelog/)

Contact: support@mef-llm-studio.com