mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2026-01-07 06:30:36 +08:00
23 lines
436 B
YAML
23 lines
436 B
YAML
### model
|
|
model_name_or_path: Qwen/Qwen3-4B-Instruct-2507
|
|
trust_remote_code: true
|
|
|
|
### method
|
|
stage: sft
|
|
do_train: true
|
|
finetuning_type: lora
|
|
lora_rank: 8
|
|
lora_target: all
|
|
|
|
### dataset
|
|
dataset: identity,alpaca_en_demo
|
|
template: qwen3_nothink
|
|
cutoff_len: 2048
|
|
max_samples: 1000
|
|
preprocessing_num_workers: 16
|
|
tokenized_path: saves/qwen3-4b/dataset/sft
|
|
|
|
### output (not used)
|
|
output_dir: saves/qwen3-4b/lora/sft
|
|
overwrite_output_dir: true
|