add model

LLaMmlein_1B.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019692f01dcff4379e0af56302a9461eb9f266653c9796992f308efa0210ff9f
+size 402502

LLaMmlein_1B.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428840e541560e11a46f49be92b978b8c344fd873d9633b39f93a5678842604c
+size 2200193792

LLaMmlein_1B.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "66E1E9FD-372C-4412-928B-F3B84A23D34B": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "C4DCB504-21DC-4A96-8097-D4B4EBAED8F5": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "66E1E9FD-372C-4412-928B-F3B84A23D34B"
+}

README.md

@@ -0,0 +1,136 @@
+---
+datasets:
+- togethercomputer/RedPajama-Data-V2
+language:
+- de
+pipeline_tag: text-generation
+library_name: coremltools
+license: other
+tags:
+- coreml
+- tinyllama
+- german-language-model
+---
+
+# LLäMmlein 1B CoreML
+
+This repository contains the CoreML version of [LLäMmlein 1B](https://huggingface.co/LSX-UniWue/LLaMmlein_1B), a German language model trained from scratch using the [Tinyllama](https://github.com/jzhang38/TinyLlama) codebase on the German portion of [RedPajama V2](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-V2).
+
+## Model Details
+
+- **Model Type**: German Language Model based on TinyLlama architecture
+- **Language:** German
+- **Framework**: CoreML
+- **Original Model:** [LSX-UniWue/LLaMmlein_1B](https://huggingface.co/LSX-UniWue/LLaMmlein_1B)
+- **Size:** 1B parameters
+- **Format:** CoreML (.mlpackage)
+- **Minimum Deployment Target:** iOS 16
+- **Compute Units:** ALL (CPU + Neural Engine)
+- **Input Sequence Length:** 512 tokens
+
+## Conversion Process
+
+The model was converted from PyTorch to CoreML using the following steps:
+
+```python
+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")
+```
+
+## Usage
+
+To use this model on Apple devices:
+
+```swift
+import CoreML
+
+// Load the model
+let config = MLModelConfiguration()
+let model = try LLaMmlein_1B(configuration: config)
+
+// Prepare input
+let inputIds = // Your tokenized input as [Int32]
+
+// Make prediction
+let prediction = try model.prediction(input_ids: inputIds)
+```
+
+## Performance Considerations
+
+- The model is optimized for Apple Neural Engine
+- Recommended for iOS 16+ devices
+- Best performance achieved with batch size of 1
+- Maximum sequence length is set to 512 tokens
+
+## Original Model Information
+
+The original model was trained on the German portion of RedPajama V2. For more details about the base model:
+- Visit the [project page](https://www.informatik.uni-wuerzburg.de/datascience/projects/nlp/llammlein/)
+- Read the [research paper](arxiv.org/abs/2411.11171)
+- Check the [SuperGLEBer benchmark](https://lsx-uniwue.github.io/SuperGLEBer-site/) for evaluation results
+
+## License
+
+This model inherits its license from the original LLäMmlein 1B model.
+
+## Citation
+
+If you use this model, please cite the original work:
+
+```bibtex
+@misc{llammlein2024,
+  title={LLäMmlein: A German Language Model},
+  author={LSX-UniWue},
+  year={2024},
+  publisher={Hugging Face},
+  journal={Hugging Face Hub},
+  howpublished={\url{https://huggingface.co/LSX-UniWue/LLaMmlein_1B}},
+}
+```
+
+For the original model description and evaluation results, see the [original model card](https://huggingface.co/LSX-UniWue/LLaMmlein_1B).

convert_model.py

@@ -0,0 +1,47 @@
+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")