mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-08-02 03:32:50 +08:00
32 lines
745 B
YAML
32 lines
745 B
YAML
# The batch generation can be SLOW using this config.
|
|
# For faster inference, we recommend to use `scripts/vllm_infer.py`.
|
|
|
|
### model
|
|
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
|
|
adapter_name_or_path: saves/llama3-8b/lora/sft
|
|
trust_remote_code: true
|
|
|
|
### method
|
|
stage: sft
|
|
do_predict: true
|
|
finetuning_type: lora
|
|
|
|
### dataset
|
|
eval_dataset: identity,alpaca_en_demo
|
|
template: llama3
|
|
cutoff_len: 2048
|
|
max_samples: 50
|
|
overwrite_cache: true
|
|
preprocessing_num_workers: 16
|
|
dataloader_num_workers: 4
|
|
|
|
### output
|
|
output_dir: saves/llama3-8b/lora/predict
|
|
overwrite_output_dir: true
|
|
report_to: none # choices: [none, wandb, tensorboard, swanlab, mlflow]
|
|
|
|
### eval
|
|
per_device_eval_batch_size: 1
|
|
predict_with_generate: true
|
|
ddp_timeout: 180000000
|