> ## Documentation Index
> Fetch the complete documentation index at: https://forge-64364c0e.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Load your first model, inspect it, train it, merge models, and run inference

## Load → Inspect → Test

<Steps>
  <Step title="Load a model">
    1. Click **Load** (01) in the sidebar
    2. Click **LOAD GGUF FILE** (or **LOAD SAFETENSORS FILE** / **LOAD MODEL FOLDER**)
    3. Select your model file in the dialog
    4. Wait for header parsing (\< 1 second)

    You'll see model metadata: architecture, layers, parameters, quantization, and tensor map.
  </Step>

  <Step title="Inspect the architecture">
    1. Click **Inspect** (02) in the sidebar
    2. Explore the isometric 3D visualization — hover layers for details
    3. Review memory distribution, quantization breakdown, and runtime compatibility
    4. Check capability detection (reasoning, code, math, etc.)
  </Step>

  <Step title="Run inference">
    1. Click **Test** (09) in the sidebar
    2. Click **USE LOADED** to select your model
    3. Type a prompt or click a quick test preset (CODE, MATH, REASON, CREATIVE, INSTRUCT, CHAT)
    4. Configure GPU layers, temperature, and max tokens
    5. Click **GENERATE** and watch tokens stream in real time
  </Step>
</Steps>

<Note>
  For GGUF inference, llama.cpp tools must be installed. Go to **Settings** (07) → llama.cpp Tools → **DOWNLOAD & INSTALL**.
</Note>

## Download → Quantize

<Steps>
  <Step title="Download from HuggingFace">
    1. Click **Hub** (04) in the sidebar
    2. Enter a repo ID (e.g., `TheBloke/Mistral-7B-Instruct-v0.2-GGUF`)
    3. Click **FETCH**, then **DOWNLOAD** on a GGUF file
  </Step>

  <Step title="Load and quantize">
    1. In Library view, click **LOAD** on the downloaded model
    2. Go to **Compress** (03)
    3. Pick a quantization preset (**MOBILE**, **BALANCED**, or **QUALITY**)
    4. Click **QUANTIZE MODEL** and choose output path
  </Step>
</Steps>

## Explore a Dataset

<Steps>
  <Step title="Load from HuggingFace">
    1. Click **DataStudio** (10) in the sidebar
    2. Switch to **HUGGINGFACE** source
    3. Enter a dataset repo ID (e.g., `tatsu-lab/alpaca`)
    4. Click **FETCH** to see available files
    5. Click **DOWNLOAD** on a Parquet or JSON file
    6. Dataset auto-loads after download
  </Step>

  <Step title="Analyze">
    Review metadata (rows, columns, format), column analysis (dtypes, null counts), and preview data in the table view.
  </Step>
</Steps>

## Fine-Tune a Model

<Steps>
  <Step title="Select model and dataset">
    1. Click **Training** (06) in the sidebar
    2. Browse for a model (GGUF or SafeTensors)
    3. Browse for a dataset (JSON, JSONL, CSV, or Parquet)
  </Step>

  <Step title="Choose method and preset">
    1. Select a training method (LoRA, QLoRA, SFT, DPO, Full)
    2. Pick a VRAM preset (LOW VRAM \~4GB, BALANCED \~6GB, QUALITY \~12GB, MAX QUALITY \~24GB)
    3. Optionally target specific capabilities (reasoning, code, math, etc.)
  </Step>

  <Step title="Train">
    Click **START TRAINING**, monitor real-time progress (loss, epoch, VRAM usage, ETA).
  </Step>
</Steps>

## Merge Two Models

<Steps>
  <Step title="Load parents">
    1. Click **M-DNA** (08) in the sidebar
    2. In the Files tab, click **+ LOAD FILE** twice to load 2 models
  </Step>

  <Step title="Configure merge">
    1. Go to Settings tab, pick a preset (**QUICK BLEND**, **SMOOTH MERGE**, **TASK TUNER**, etc.)
    2. Or manually select a method and tune parameters
    3. Set output format (SafeTensors or GGUF) and output path
  </Step>

  <Step title="Build">
    1. Click **BUILD MERGE**
    2. Monitor progress in the sidebar and status bar
    3. Result shows output path and size
  </Step>
</Steps>