lucy li

how to finetune in single gpu

1

cd finetune && deepspeed finetune_deepseekcoder.py --model_name_or_path $MODEL_PATH --data_path $DATA_PATH --output_dir $OUTPUT_PATH --num_train_epochs 3 --model_max_length 1024 --per_device_train_batch_size 16 --per_device_eval_batch_size 1 --gradient_accumulation_steps 4 --evaluation_strategy "no" --save_strategy "steps" --save_steps 100 --save_total_limit 100 --learning_rate...

A problem about your function compare_layer_output in converter_v2.py

5

When I add the code : compare_layer_output(net, 'conv1', checkpoint, 'MobilenetV2/Conv/Conv2D:0', image_file) in converter_v2.py error occurs: ('Save converted caffemodel to', 'caffemodel_fromckpt/mobilenet_v2_1.0_224.caffemodel') Traceback (most recent call last): File "converter_v2.py", line 297, in...

do not leverage temporal information

1

如果我不想用transformer中的 时序注意力机制，可以直接在配置文件中修改吗 还是得改代码