cli.merge_lora
cli.merge_lora
CLI to merge a trained LoRA into a base model.
Functions
| Name | Description |
|---|---|
| do_cli | Parses axolotl config, CLI args, and calls do_merge_lora. Note that various |
| do_merge_lora | Calls transformers’ merge_and_unload on the model given in the axolotl config |
do_cli
cli.merge_lora.do_cli(config=Path('examples/'), **kwargs)Parses axolotl config, CLI args, and calls do_merge_lora. Note that various
config values will be overwritten to allow the LoRA merge logic to work as expected
(load_in_8bit=False, load_in4bit=False, flash_attention=False, etc.).
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
| config | Union[Path, str] | Path to axolotl config YAML file. |
Path('examples/') |
| kwargs | Additional keyword arguments to override config file values. | {} |
Raises
| Name | Type | Description |
|---|---|---|
| ValueError | If target directory for LoRA merged model does not exist. |
do_merge_lora
cli.merge_lora.do_merge_lora(cfg)Calls transformers’ merge_and_unload on the model given in the axolotl config
along with the LoRA adapters to combine them into a single base model.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
| cfg | DictDefault | Dictionary mapping axolotl config keys to values. |
required |