Trying out OpenAI Text Generation

I am following the directions here:

https://github.com/openai/gpt-2/blob/master/DEVELOPERS.md

I created a Linode 2GB.

When I run

python3 src/interactive_conditional_samples.py --top_k 40 --model_name=355M

I get an error:

python3 src/interactive_conditional_samples.py --top_k 40 --model_name=355M
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
2019-11-09 18:07:41.204054: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-11-09 18:07:41.241454: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 1999990000 Hz
2019-11-09 18:07:41.242825: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x22bce70 executing computations on platform Host. Devices:
2019-11-09 18:07:41.242993: I tensorflow/compiler/xla/service/service.cc:158]   StreamExecutor device (0): , 
WARNING:tensorflow:From /usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /root/gpt-2/src/sample.py:64: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
WARNING:tensorflow:From /root/gpt-2/src/sample.py:67: multinomial (from tensorflow.python.ops.random_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.random.categorical instead.
WARNING:tensorflow:From /usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
2019-11-09 18:08:01.779891: W tensorflow/core/framework/allocator.cc:124] Allocation of 205852672 exceeds 10% of system memory.
Killed

When I don’t specify a model_name or specify 124M it works fine.

python3 src/interactive_conditional_samples.py --top_k 40 --model_name=124M

Leave a Reply