from transformers import AutoModelForCausalLM, AutoTokenizer

# Set the path to your model and tokenizer
model_directory = "/workspace/mergekit/output-model-directory"
tokenizer_directory = "/workspace/mergekit/output-model-directory"

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(tokenizer_directory, ignore_mismatched_sizes=True)
# Load the model
model = AutoModelForCausalLM.from_pretrained(model_directory, ignore_mismatched_sizes=True)

input_text = "Example input text here"
inputs = tokenizer(input_text, return_tensors="pt")

# Generate predictions
outputs = model.generate(inputs['input_ids'], max_length=50)

# Decode generated ids to text
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)