#
4. Checking Training Results
Running the train_qwen.py
script, as in the previous chapter, will save the resulting model in the qwen_code_generation
directory. This is a pure PyTorch model parameter file and is fully compatible with regular GPU servers, not just the MoAI Platform.
You can test the trained model using the inference_qwen.py
script located under the tutorial
directory in the GitHub repository you downloaded earlier. In the test, the prompt "Given a list of strings, create a function that joins them with spaces" was used.
# tutorial/inference_qwen.py
...
input_text = """Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Create a function to join given list of strings with space.
### Input:
['I', 'love', 'you']
### Output:
"""
Run the code below.
~/quickstart$ python tutorial/inference_qwen.py
Upon examining the output, you can confirm that the model has appropriately generated the function as per the prompt.
Qwen: Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Create a function to join given list of strings with space.
### Input:
['I', 'love', 'you']
### Output:
def join_strings(string_list):
return ' '.join(string_list)
result = join_strings(['I', 'love', 'you'])
print(result)