File size: 1,240 Bytes
c8027be |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
kwargs = {
'per_device_train_batch_size': 2,
'save_steps': 5,
'gradient_accumulation_steps': 4,
'num_train_epochs': 1,
}
def test_llm():
from swift.llm import rlhf_main, RLHFArguments, infer_main, InferArguments
result = rlhf_main(
RLHFArguments(
rlhf_type='kto',
model='Qwen/Qwen2-7B-Instruct',
dataset=['AI-ModelScope/ultrafeedback-binarized-preferences-cleaned-kto#100'],
**kwargs))
last_model_checkpoint = result['last_model_checkpoint']
infer_main(InferArguments(adapters=last_model_checkpoint, load_data_args=True, merge_lora=True))
def test_mllm():
from swift.llm import rlhf_main, RLHFArguments, infer_main, InferArguments
result = rlhf_main(
RLHFArguments(
rlhf_type='kto',
model='Qwen/Qwen2-VL-7B-Instruct',
dataset=['AI-ModelScope/ultrafeedback-binarized-preferences-cleaned-kto#100'],
**kwargs))
last_model_checkpoint = result['last_model_checkpoint']
infer_main(InferArguments(adapters=last_model_checkpoint, load_data_args=True, merge_lora=True))
if __name__ == '__main__':
# test_llm()
test_mllm()
|