We provide a simple finetuning commands (litgpt finetune *) that instruction-finetune a pretrained model on datasets such as Alpaca, Dolly, and others. For more information on the supported instruction datasets and how to prepare your own custom datasets, please see the tutorials/prepare_dataset tutorials.
LitGPT currently supports the following finetuning methods:
litgpt finetune full
litgpt finetune lora
litgpt finetune adapter
litgpt finetune adapter_v2The following section provides more details about these methods, including links for additional resources.
The section below provides additional information on the available and links to further resources.
litgpt finetune fullThis method trains all model weight parameters and is the most memory-intensive finetuning technique in LitGPT.
More information and resources:
- the LitGPT tutorials/finetune_full tutorial
litgpt finetune loraLoRA and QLoRA are parameter-efficient finetuning technique that only require updating a small number of parameters, which makes this a more memory-efficienty alternative to full finetuning.
More information and resources:
- the LitGPT tutorials/finetune_lora tutorial
- the LoRA paper by (Hu et al. 2021)
- the conceptual tutorial Parameter-Efficient LLM Finetuning With Low-Rank Adaptation (LoRA)
litgpt finetune adapteror
litgpt finetune adapter_v2Similar to LoRA, adapter finetuning is a parameter-efficient finetuning technique that only requires training a small subset of weight parameters, making this finetuning method more memory-efficient than full-parameter finetuning.
More information and resources:
- the LitGPT tutorials/finetune_adapter tutorial
- the Llama-Adapter (Gao et al. 2023) and Llama-Adapter v2 (Zhang et al. 2023) papers that originally introduces these methods
- the conceptual tutorial Understanding Parameter-Efficient Finetuning of Large Language Models: From Prefix Tuning to LLaMA-Adapters