# Fine-tuning (14)

Teach a model your data and style.

| slug | name | tier | stars | what | md |
|---|---|---|---|---|---|
| unsloth | Unsloth | catalog | 78064 | Fast, low-memory fine-tuning with a local UI. | /setups/unsloth.md |
| llama-factory | LLaMA-Factory | catalog | 75495 | Fine-tune 100+ LLMs and VLMs from one tool. | /setups/llama-factory.md |
| nanogpt | nanoGPT | catalog | 63835 | The simplest repo to train small GPTs. | /setups/nanogpt.md |
| nanochat | nanochat | catalog | 58660 | Train a small ChatGPT end to end on a budget. | /setups/nanochat.md |
| open-r1 | Open R1 | catalog | 26481 | Open reproduction of DeepSeek-R1 training. | /setups/open-r1.md |
| verl | verl | catalog | 23891 | Reinforcement-learning post-training framework. | /setups/verl.md |
| peft | PEFT | catalog | 21790 | LoRA and other parameter-efficient fine-tuning. | /setups/peft.md |
| trl | TRL | catalog | 19519 | Train models with SFT, DPO and RL. | /setups/trl.md |
| ms-swift | ms-swift | catalog | 15860 | Fine-tune 600+ LLMs with PEFT or full training. | /setups/ms-swift.md |
| axolotl | Axolotl | catalog | 12572 | Config-driven fine-tuning toolkit. | /setups/axolotl.md |
| openrlhf | OpenRLHF | catalog | 10089 | Scalable RLHF and agentic RL on Ray. | /setups/openrlhf.md |
| oumi | Oumi | catalog | 9401 | Fine-tune, evaluate and deploy open models. | /setups/oumi.md |
| mergekit | MergeKit | catalog | 7402 | Merge model weights into new models. | /setups/mergekit.md |
| mlx-lm-lora | MLX-LM-LoRA | catalog | 434 | LoRA and full fine-tuning on MLX. | /setups/mlx-lm-lora.md |