24 lines
403 B
YAML
24 lines
403 B
YAML
|
# model
|
||
|
|
model_name_or_path: saves/llama3-8b/full/sft
|
||
|
|
|
||
|
|
# method
|
||
|
|
stage: sft
|
||
|
|
do_predict: true
|
||
|
|
finetuning_type: full
|
||
|
|
|
||
|
|
# dataset
|
||
|
|
dataset: identity,alpaca_gpt4_en
|
||
|
|
template: llama3
|
||
|
|
cutoff_len: 1024
|
||
|
|
max_samples: 50
|
||
|
|
overwrite_cache: true
|
||
|
|
preprocessing_num_workers: 16
|
||
|
|
|
||
|
|
# output
|
||
|
|
output_dir: saves/llama3-8b/full/predict
|
||
|
|
overwrite_output_dir: true
|
||
|
|
|
||
|
|
# eval
|
||
|
|
per_device_eval_batch_size: 1
|
||
|
|
predict_with_generate: true
|