# 4. Checking Training Results

Running the train_mistral.py script, as in the previous section, will save the resulting model in the mistral_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_mistral.py script located in the tutorial directory of the GitHub repository you downloaded earlier. In this test, the prompt "Create a function that takes a list of strings as input and joins them with spaces" was used.

# tutorial/inference_mistral.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:\n['I', 'love', 'you']

### Output:
"""

Run the code below.

~/quickstart$ python tutorial/inference_mistral.py

Upon examining the output, you can confirm that the model has appropriately generated the function as per the prompt.

Mistral: 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', 'Moreh']

### Output:
def join_strings(string_list):
		return ' '.join(string_list)

result = join_strings(['I', 'love', 'Moreh'])
print(result)

tutorial mistral