Migration

Switch to Soup from other fine-tuning tools in one command. Soup automatically converts your existing config files.

Supported Tools

Usage

# Convert LLaMA-Factory config to soup.yaml
soup migrate --from llamafactory llama3_lora_sft.yaml

# Convert Axolotl config
soup migrate --from axolotl axolotl_config.yml

# Convert Unsloth notebook (AST-only, no code execution)
soup migrate --from unsloth finetune.ipynb

# Preview without writing (dry-run)
soup migrate --from llamafactory config.yaml --dry-run

# Custom output path
soup migrate --from axolotl config.yml --output my-soup.yaml

What Gets Mapped

Soup maps all major config fields automatically:

• Model: model_name_or_path / base_model -> base
• Task: stage / rl -> task (pt->pretrain, rm->reward_model, sft/dpo/kto/ppo/grpo)
• LoRA: rank, alpha, dropout, target modules, DoRA
• Training: epochs, lr, batch size, optimizer, scheduler, warmup, quantization
• Data: dataset path, format, max length
• Output: output directory

Unsupported Features

Soup will warn about features that don't have a direct equivalent:

• sample_packing (Axolotl) — no Soup equivalent yet
• freeze training (LLaMA-Factory) — partial parameter freezing
• use_rslora (Unsloth) — now supported via training.use_rslora in Soup v0.21.0+
• max_steps — Soup uses epochs; max_steps emitted as comment
• DeepSpeed / W&B — emitted as CLI flag comments

Security

• Input files are validated to be within the current working directory
• Unsloth notebooks are parsed via AST only — no code is executed
• Output paths are confined to the current directory