convert_model.py

import torch
import numpy as np
from transformers import AutoModelForCausalLM, AutoTokenizer
import coremltools as ct

# Load model and convert to TorchScript
model = AutoModelForCausalLM.from_pretrained("LSX-UniWue/LLaMmlein_1B")
tokenizer = AutoTokenizer.from_pretrained("LSX-UniWue/LLaMmlein_1B")

# Set model to eval mode
model.eval()

# Create example input
text = "Ein Beispieltext"
inputs = tokenizer(text, return_tensors="pt")

# Create a wrapper class for tracing
class ModelWrapper(torch.nn.Module):
    def __init__(self, model):
        super().__init__()
        self.model = model

    def forward(self, input_ids):
        return self.model(input_ids).logits

# Wrap and trace model
wrapped_model = ModelWrapper(model)
traced_model = torch.jit.trace(wrapped_model, inputs.input_ids)

# Convert to CoreML
model_mlpackage = ct.convert(
    traced_model,
    inputs=[
        ct.TensorType(
            name="input_ids",
            shape=inputs.input_ids.shape,
            dtype=np.int32
        )
    ],
    source="pytorch",
    minimum_deployment_target=ct.target.iOS16,
    convert_to="mlprogram",
    compute_precision=ct.precision.FLOAT16,
    compute_units=ct.ComputeUnit.ALL,
)

model_mlpackage.save("LLaMmlein_1B.mlpackage")