Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,153 @@
+---
+license: mit
+tags:
+- coreml
+- ANE
+- LLaMA
+- Qwen
+- DeepSeek
+- Gemma
+- Apple
+- Apple Neural Engine
+- DeepHermes
+---
+# ANEMLL
+
+**ANEMLL** (pronounced like "animal") is an open-source project focused on accelerating the porting of Large Language Models (LLMs) to tensor processors, starting with the Apple Neural Engine (ANE).
+
+The goal is to provide a fully open-source pipeline from model conversion to inference for common LLM architectures running on ANE.
+
+This enables seamless integration and on-device inference for low-power applications on edge devices, ensuring maximum privacy and security.
+
+This is critical for autonomous applications, where models run directly on the device without requiring an internet connection.
+
+For more information, visit the [ANEMLL GitHub repository](https://github.com/anemll/anemll).
+
+
+---
+
+## License
+
+ANEMLL is licensed under the [MIT License](https://opensource.org/license/mit).
+The original model may require a separate license depending on the architecture:
+- LLaMA models: Based on Meta's LLaMA and may require Meta's license
+- Qwen models: Based on Alibaba's Qwen and may require Alibaba's license
+- Gemma models: Based on Google's Gemma and subject to Gemma Terms of Use
+- Other models: Check respective original model licenses
+
+This model is converted for CoreML using ANEMLL's open-source conversion pipeline. It supports multiple LLM architectures including LLaMA, Qwen, Gemma, and DeepSeek variants.
+
+---
+
+## Requirements
+
+- **macOS 15 (Sequoia)** or later with Apple Neural Engine and 8GB RAM or more
+- **CoreML Tools 8.x+** and **HuggingFace Transformers** libraries
+- **Python 3.9+**
+
+`chat.py` provides a sample inference script.  
+`chat_full.py` provides a sample inference script with history and conversation management.  
+
+**Installation**
+
+1. Download the model from Hugging Face:
+```bash
+# Install required tools
+pip install huggingface_hub
+
+# Install Git LFS (Large File Support)
+# macOS with Homebrew:
+brew install git-lfs
+# Or Ubuntu/Debian:
+# sudo apt-get install git-lfs
+
+# Initialize Git LFS
+git lfs install
+
+# Clone the repository with model files
+git clone https://huggingface.co/anemll/anemll-google-gemma-3-1b-it-ctx512_0.3.5
+```
+
+2. Extract model files:
+```bash
+# Navigate to cloned directory
+cd anemll-google-gemma-3-1b-it-ctx512_0.3.5
+
+# Pull LFS files (model weights)
+git lfs pull
+
+# Extract CoreML model files
+find . -type f -name "*.zip" -exec unzip {} \;
+```
+
+3. Install dependencies:
+```bash
+pip install coremltools transformers
+```
+
+**Coremltools:**
+
+See coremltools installation guide at https://apple.github.io/coremltools/docs-guides/source/installing-coremltools.html 
+
+**How to Run**
+
+1. Basic chat interface:
+```bash
+python chat.py --meta ./meta.yaml
+```
+
+2. Full conversation mode with history:
+```bash
+python chat_full.py --meta ./meta.yaml
+```
+
+> Note: The first time the model loads, macOS will take some time to place it on the device.
+> Subsequent loads will be instantaneous.
+> Use Ctrl-D to exit, Ctrl-C to interrupt inference.
+
+**More Info**
+Please check following links for later updates:
+
+* [GitHub](https://github.com/anemll)
+* [Hugging Face Models](https://huggingface.co/anemll)
+* [Twitter/X](https://x.com/anemll)
+* [Website](https://anemll.com)
+
+
+realanemll@gmail.com
+
+# anemll-google-gemma-3-1b-it-ctx512_0.3.5
+
+This is a CoreML model converted using ANEMLL for Apple Neural Engine inference.
+
+## Available Distributions
+
+### Standard Distribution
+- Contains zipped MLMODELC files
+- Suitable for macOS and development
+
+### iOS Distribution
+- Contains unzipped MLMODELC files
+- Ready for iOS deployment
+- Includes offline tokenizer support
+
+## Model Information
+- Context Length: 512
+- Batch Size: 64
+- Number of Chunks: 2
+- LUT Quantization: none
+
+## Quick Start
+
+### Test in iOS/macOS App
+Try our sample Chat-Bot app on TestFlight:
+1. Install TestFlight from App Store
+2. Join beta test: [TestFlight Link](https://testflight.apple.com/join/jrQq1D1C)
+3. App includes a small demo model pre-installed
+4. You can add custom models via HuggingFace URLs
+
+> [!Note]
+> - The TestFlight app works on both iOS and macOS
+> - Demonstrates proper model integration and provides a reference implementation
+> - iOS requires unzipped MLMODELC files and config.json for offline tokenizer
+> - macOS supports both zipped and unzipped model formats

config.json

@@ -0,0 +1,4 @@
+{
+  "tokenizer_class": "GemmaTokenizer",
+  "model_type": "gemma"
+}

gemma3_FFN_PF_chunk_01of02.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dafc6f3933b3b4504e7308d2a3c9f965c5123412036d6d5289914846f7ac2a0
+size 243

gemma3_FFN_PF_chunk_01of02.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd2b467d25e8ae57624fe12d4a6122adcdcd8a8ab9fcf3e0636bddd18430184
+size 953

gemma3_FFN_PF_chunk_01of02.mlmodelc/metadata.json

@@ -0,0 +1,317 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.anemll.context_length" : "512",
+      "com.anemll.num_chunks" : "2",
+      "com.anemll.info" : "Converted with Anemll v0.3.5",
+      "com.anemll.batch_size" : "64",
+      "com.anemll.chunk_no" : "1"
+    },
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1152]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "position_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "causal_mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "current_pos",
+        "type" : "MultiArray"
+      }
+    ],
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1152]",
+        "name" : "output_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "storagePrecision" : "Float16",
+    "method" : "predict",
+    "functions" : [
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1152]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1, 512]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Float16",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 52 × 1 × 512 × 256)",
+            "shortDescription" : "",
+            "shape" : "[52, 1, 512, 256]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1152]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "infer",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.softmax" : 13,
+          "Ios18.expandDims" : 26,
+          "Ios18.mul" : 260,
+          "Ios18.matmul" : 26,
+          "Identity" : 1,
+          "Ios18.greaterEqual" : 1,
+          "Select" : 1,
+          "Ios18.readState" : 27,
+          "Tile" : 26,
+          "Ios18.gather" : 4,
+          "Ios18.add" : 67,
+          "Ios18.layerNorm" : 78,
+          "Ios18.sliceUpdate" : 26,
+          "Ios18.writeState" : 26,
+          "Ios18.reshape" : 56,
+          "Ios18.conv" : 91,
+          "Ios18.gelu" : 13,
+          "Ios18.concat" : 156,
+          "Ios18.transpose" : 78,
+          "Ios18.cast" : 4,
+          "Ios18.sliceByIndex" : 156,
+          "Ios18.squeeze" : 13
+        }
+      },
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 64 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 64, 1152]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 64)",
+            "shortDescription" : "",
+            "shape" : "[64]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 64 × 512)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 64, 512]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Float16",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 52 × 1 × 512 × 256)",
+            "shortDescription" : "",
+            "shape" : "[52, 1, 512, 256]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 64 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 64, 1152]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "prefill",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.softmax" : 13,
+          "Ios18.expandDims" : 26,
+          "Ios18.mul" : 260,
+          "Ios18.matmul" : 26,
+          "Ios18.greaterEqual" : 1,
+          "Select" : 1,
+          "Ios18.readState" : 27,
+          "Tile" : 26,
+          "Ios18.gather" : 4,
+          "Ios18.add" : 67,
+          "Ios18.layerNorm" : 78,
+          "Ios18.sliceUpdate" : 26,
+          "Ios18.writeState" : 26,
+          "Ios18.reshape" : 95,
+          "Ios18.conv" : 91,
+          "Ios18.gelu" : 13,
+          "Ios18.concat" : 156,
+          "Ios18.transpose" : 121,
+          "Ios18.cast" : 4,
+          "Ios18.sliceByIndex" : 156,
+          "Ios18.squeeze" : 13
+        }
+      }
+    ],
+    "version" : "0.3.5",
+    "isUpdatable" : "0",
+    "defaultFunctionName" : "infer",
+    "specificationVersion" : 9,
+    "stateSchema" : [
+      {
+        "dataType" : "Float16",
+        "isOptional" : "0",
+        "formattedType" : "State (Float16 52 × 1 × 512 × 256)",
+        "shortDescription" : "",
+        "shape" : "[52, 1, 512, 256]",
+        "name" : "model_model_kv_cache_0",
+        "type" : "State"
+      }
+    ],
+    "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.softmax" : 13,
+      "Ios18.expandDims" : 26,
+      "Ios18.mul" : 260,
+      "Ios18.matmul" : 26,
+      "Identity" : 1,
+      "Ios18.greaterEqual" : 1,
+      "Select" : 1,
+      "Ios18.readState" : 27,
+      "Tile" : 26,
+      "Ios18.gather" : 4,
+      "Ios18.add" : 67,
+      "Ios18.layerNorm" : 78,
+      "Ios18.sliceUpdate" : 26,
+      "Ios18.writeState" : 26,
+      "Ios18.reshape" : 56,
+      "Ios18.conv" : 91,
+      "Ios18.gelu" : 13,
+      "Ios18.concat" : 156,
+      "Ios18.transpose" : 78,
+      "Ios18.cast" : 4,
+      "Ios18.sliceByIndex" : 156,
+      "Ios18.squeeze" : 13
+    },
+    "shortDescription" : "Anemll Model: Multifunction FFN+Prefill",
+    "generatedClassName" : "gemma3_FFN_PF_chunk_01of02",
+    "author" : "Converted with Anemll v0.3.5",
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    }
+  }
+]

gemma3_FFN_PF_chunk_01of02.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b142c51be9abc0d1ed8b63f4286b38e4843a0080ce84ab7168e2d135700c8a14
+size 700003200

gemma3_FFN_PF_chunk_02of02.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d1f32803f044c836158996b82cb66d150e89530f096468a45e3f145a925f87
+size 243

gemma3_FFN_PF_chunk_02of02.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f667d6722c60dfe1569e0217b44f795255607a8115576c5991ef3cd2c5349b56
+size 953

gemma3_FFN_PF_chunk_02of02.mlmodelc/metadata.json

@@ -0,0 +1,317 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.anemll.context_length" : "512",
+      "com.anemll.num_chunks" : "2",
+      "com.anemll.info" : "Converted with Anemll v0.3.5",
+      "com.anemll.batch_size" : "64",
+      "com.anemll.chunk_no" : "2"
+    },
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1152]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "position_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "causal_mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "current_pos",
+        "type" : "MultiArray"
+      }
+    ],
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1152]",
+        "name" : "output_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "storagePrecision" : "Float16",
+    "method" : "predict",
+    "functions" : [
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1152]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1, 512]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Float16",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 52 × 1 × 512 × 256)",
+            "shortDescription" : "",
+            "shape" : "[52, 1, 512, 256]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1152]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "infer",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.softmax" : 13,
+          "Ios18.expandDims" : 26,
+          "Ios18.mul" : 262,
+          "Ios18.matmul" : 26,
+          "Identity" : 1,
+          "Ios18.greaterEqual" : 1,
+          "Select" : 1,
+          "Ios18.readState" : 27,
+          "Tile" : 26,
+          "Ios18.gather" : 4,
+          "Ios18.add" : 67,
+          "Ios18.layerNorm" : 79,
+          "Ios18.sliceUpdate" : 26,
+          "Ios18.writeState" : 26,
+          "Ios18.reshape" : 56,
+          "Ios18.conv" : 91,
+          "Ios18.gelu" : 13,
+          "Ios18.concat" : 157,
+          "Ios18.transpose" : 78,
+          "Ios18.cast" : 4,
+          "Ios18.sliceByIndex" : 157,
+          "Ios18.squeeze" : 13
+        }
+      },
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 64 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 64, 1152]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 64)",
+            "shortDescription" : "",
+            "shape" : "[64]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 64 × 512)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 64, 512]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Float16",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 52 × 1 × 512 × 256)",
+            "shortDescription" : "",
+            "shape" : "[52, 1, 512, 256]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1152]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "prefill",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.softmax" : 13,
+          "Ios18.expandDims" : 26,
+          "Ios18.mul" : 260,
+          "Ios18.matmul" : 26,
+          "Ios18.greaterEqual" : 1,
+          "Select" : 1,
+          "Ios18.readState" : 27,
+          "Tile" : 26,
+          "Ios18.gather" : 4,
+          "Ios18.add" : 67,
+          "Ios18.layerNorm" : 78,
+          "Ios18.sliceUpdate" : 26,
+          "Ios18.writeState" : 26,
+          "Ios18.reshape" : 95,
+          "Ios18.conv" : 91,
+          "Ios18.gelu" : 13,
+          "Ios18.concat" : 156,
+          "Ios18.transpose" : 121,
+          "Ios18.cast" : 4,
+          "Ios18.sliceByIndex" : 157,
+          "Ios18.squeeze" : 13
+        }
+      }
+    ],
+    "version" : "0.3.5",
+    "isUpdatable" : "0",
+    "defaultFunctionName" : "infer",
+    "specificationVersion" : 9,
+    "stateSchema" : [
+      {
+        "dataType" : "Float16",
+        "isOptional" : "0",
+        "formattedType" : "State (Float16 52 × 1 × 512 × 256)",
+        "shortDescription" : "",
+        "shape" : "[52, 1, 512, 256]",
+        "name" : "model_model_kv_cache_0",
+        "type" : "State"
+      }
+    ],
+    "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.softmax" : 13,
+      "Ios18.expandDims" : 26,
+      "Ios18.mul" : 262,
+      "Ios18.matmul" : 26,
+      "Identity" : 1,
+      "Ios18.greaterEqual" : 1,
+      "Select" : 1,
+      "Ios18.readState" : 27,
+      "Tile" : 26,
+      "Ios18.gather" : 4,
+      "Ios18.add" : 67,
+      "Ios18.layerNorm" : 79,
+      "Ios18.sliceUpdate" : 26,
+      "Ios18.writeState" : 26,
+      "Ios18.reshape" : 56,
+      "Ios18.conv" : 91,
+      "Ios18.gelu" : 13,
+      "Ios18.concat" : 157,
+      "Ios18.transpose" : 78,
+      "Ios18.cast" : 4,
+      "Ios18.sliceByIndex" : 157,
+      "Ios18.squeeze" : 13
+    },
+    "shortDescription" : "Anemll Model: Multifunction FFN+Prefill",
+    "generatedClassName" : "gemma3_FFN_PF_chunk_02of02",
+    "author" : "Converted with Anemll v0.3.5",
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    }
+  }
+]

gemma3_FFN_PF_chunk_02of02.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7b695eac0eb83745e0887f138cd5bfefa3ae8dd27b97728743538ef443ef26
+size 700005568

gemma3_embeddings.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27a0e12ebbb87563fc5f75c8627012001299ad279758beb88ac2b2f0463821d
+size 243

gemma3_embeddings.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac0bca33ec9a564620ebd2c064f1d361f56c1dcc0401fc21de9af80968b25ab
+size 559

gemma3_embeddings.mlmodelc/metadata.json

@@ -0,0 +1,72 @@
+[
+  {
+    "shortDescription" : "Anemll Model (Embeddings) converted to CoreML",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16)",
+        "shortDescription" : "",
+        "shape" : "[]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "0.3.5",
+    "modelParameters" : [
+
+    ],
+    "author" : "Converted with Anemll v0.3.5",
+    "specificationVersion" : 9,
+    "storagePrecision" : "Float16",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.greaterEqual" : 1,
+      "Ios18.add" : 1,
+      "Select" : 1,
+      "Ios18.gather" : 1,
+      "Ios18.mul" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "shortDescription" : "",
+        "dataType" : "Int32",
+        "hasShapeFlexibility" : "1",
+        "isOptional" : "0",
+        "shapeFlexibility" : "1 × 1 | 1 × 64",
+        "formattedType" : "MultiArray (Int32 1 × 1)",
+        "type" : "MultiArray",
+        "shape" : "[1, 1]",
+        "name" : "input_ids",
+        "enumeratedShapes" : "[[1, 1], [1, 64]]"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.conversion_date" : "2026-02-05",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.anemll.info" : "Converted with Anemll v0.3.5",
+      "com.anemll.context_length" : "512"
+    },
+    "generatedClassName" : "gemma3_embeddings",
+    "method" : "predict"
+  }
+]

gemma3_embeddings.mlmodelc/model.mil

@@ -0,0 +1,18 @@
+program(1.3)
+[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3510.2.1"}, {"coremlc-version", "3500.32.1"}, {"coremltools-component-torch", "2.5.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "9.0"}})]
+{
+    func main<ios18>(tensor<int32, [1, ?]> input_ids) [FlexibleShapeInformation = tuple<tuple<string, dict<string, tensor<int32, [?]>>>, tuple<string, dict<string, dict<string, tensor<int32, [?]>>>>>((("DefaultShapes", {{"input_ids", [1, 1]}}), ("EnumeratedShapes", {{"79ae981e", {{"input_ids", [1, 1]}}}, {"ed9b58c8", {{"input_ids", [1, 64]}}}})))] {
+            tensor<fp16, [262144, 1152]> embed_tokens_weight = const()[name = string("embed_tokens_weight"), val = tensor<fp16, [262144, 1152]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64)))];
+            int32 hidden_states_1_batch_dims_0 = const()[name = string("hidden_states_1_batch_dims_0"), val = int32(0)];
+            bool hidden_states_1_validate_indices_0 = const()[name = string("hidden_states_1_validate_indices_0"), val = bool(false)];
+            int32 greater_equal_0_y_0 = const()[name = string("greater_equal_0_y_0"), val = int32(0)];
+            tensor<bool, [1, ?]> greater_equal_0 = greater_equal(x = input_ids, y = greater_equal_0_y_0)[name = string("greater_equal_0")];
+            int32 slice_by_index_0 = const()[name = string("slice_by_index_0"), val = int32(262144)];
+            tensor<int32, [1, ?]> add_0 = add(x = input_ids, y = slice_by_index_0)[name = string("add_0")];
+            tensor<int32, [1, ?]> select_0 = select(a = input_ids, b = add_0, cond = greater_equal_0)[name = string("select_0")];
+            int32 hidden_states_1_axis_1 = const()[name = string("hidden_states_1_axis_1"), val = int32(0)];
+            tensor<fp16, [1, ?, 1152]> hidden_states_1 = gather(axis = hidden_states_1_axis_1, batch_dims = hidden_states_1_batch_dims_0, indices = select_0, validate_indices = hidden_states_1_validate_indices_0, x = embed_tokens_weight)[name = string("hidden_states_1")];
+            fp16 var_7_to_fp16 = const()[name = string("op_7_to_fp16"), val = fp16(0x1.0f8p+5)];
+            tensor<fp16, [1, ?, 1152]> hidden_states = mul(x = hidden_states_1, y = var_7_to_fp16)[name = string("hidden_states_cast_fp16")];
+        } -> (hidden_states);
+}

gemma3_embeddings.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7f442d5b2972d56a7eab76c51005254a18e98045f75ee43fbb1fe313ed01fe
+size 603979904

gemma3_lm_head.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495f4e1f1aad7acc4effbae1aba3865e5a76acd9c165613fa2877b5953ca457d
+size 243

gemma3_lm_head.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0978aceaf36c84934258bdd30438a245ac855a2f93cbb530671e38b4452945b5
+size 572

gemma3_lm_head.mlmodelc/metadata.json

@@ -0,0 +1,83 @@
+[
+  {
+    "shortDescription" : "Anemll Model (LM Head) converted to CoreML",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 16)",
+        "shortDescription" : "",
+        "shape" : "[16]",
+        "name" : "argmax_idx",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 16)",
+        "shortDescription" : "",
+        "shape" : "[16]",
+        "name" : "argmax_val",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "0.3.5",
+    "modelParameters" : [
+
+    ],
+    "author" : "Converted with Anemll v0.3.5",
+    "specificationVersion" : 9,
+    "storagePrecision" : "Float16",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.squeeze" : 20,
+      "Ios18.reduceArgmax" : 16,
+      "Ios18.concat" : 2,
+      "Ios18.transpose" : 17,
+      "Ios18.gatherAlongAxis" : 16,
+      "Ios18.expandDims" : 1,
+      "Ios18.conv" : 16,
+      "Ios18.cast" : 18
+    },
+    "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1152)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1152]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-02-05",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.anemll.context_length" : "512",
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.anemll.info" : "Converted with Anemll v0.3.5",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "gemma3_lm_head",
+    "method" : "predict"
+  }
+]

gemma3_lm_head.mlmodelc/model.mil

@@ -0,0 +1,348 @@
+program(1.3)
+[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3510.2.1"}, {"coremlc-version", "3500.32.1"}, {"coremltools-component-torch", "2.5.0"}, {"coremltools-source-dialect", "TorchScript"}, {"coremltools-version", "9.0"}})]
+{
+    func main<ios18>(tensor<fp16, [1, 1, 1152]> hidden_states) {
+            tensor<int32, [3]> var_5 = const()[name = string("op_5"), val = tensor<int32, [3]>([0, 2, 1])];
+            tensor<int32, [1]> input_axes_0 = const()[name = string("input_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 1152, 1]> var_6_cast_fp16 = transpose(perm = var_5, x = hidden_states)[name = string("transpose_16")];
+            tensor<fp16, [1, 1152, 1, 1]> input_cast_fp16 = expand_dims(axes = input_axes_0, x = var_6_cast_fp16)[name = string("input_cast_fp16")];
+            string var_29_pad_type_0 = const()[name = string("op_29_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_29_strides_0 = const()[name = string("op_29_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_29_pad_0 = const()[name = string("op_29_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_29_dilations_0 = const()[name = string("op_29_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_29_groups_0 = const()[name = string("op_29_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_9_promoted_to_fp16 = const()[name = string("op_9_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_29_cast_fp16 = conv(dilations = var_29_dilations_0, groups = var_29_groups_0, pad = var_29_pad_0, pad_type = var_29_pad_type_0, strides = var_29_strides_0, weight = var_9_promoted_to_fp16, x = input_cast_fp16)[name = string("op_29_cast_fp16")];
+            tensor<int32, [1]> var_31_axes_0 = const()[name = string("op_31_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_31_cast_fp16 = squeeze(axes = var_31_axes_0, x = var_29_cast_fp16)[name = string("op_31_cast_fp16")];
+            tensor<int32, [3]> logits_1_perm_0 = const()[name = string("logits_1_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_55_pad_type_0 = const()[name = string("op_55_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_55_strides_0 = const()[name = string("op_55_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_55_pad_0 = const()[name = string("op_55_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_55_dilations_0 = const()[name = string("op_55_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_55_groups_0 = const()[name = string("op_55_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_35_promoted_to_fp16 = const()[name = string("op_35_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(37748864)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_55_cast_fp16 = conv(dilations = var_55_dilations_0, groups = var_55_groups_0, pad = var_55_pad_0, pad_type = var_55_pad_type_0, strides = var_55_strides_0, weight = var_35_promoted_to_fp16, x = input_cast_fp16)[name = string("op_55_cast_fp16")];
+            tensor<int32, [1]> var_57_axes_0 = const()[name = string("op_57_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_57_cast_fp16 = squeeze(axes = var_57_axes_0, x = var_55_cast_fp16)[name = string("op_57_cast_fp16")];
+            tensor<int32, [3]> logits_3_perm_0 = const()[name = string("logits_3_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_81_pad_type_0 = const()[name = string("op_81_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_81_strides_0 = const()[name = string("op_81_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_81_pad_0 = const()[name = string("op_81_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_81_dilations_0 = const()[name = string("op_81_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_81_groups_0 = const()[name = string("op_81_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_61_promoted_to_fp16 = const()[name = string("op_61_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(75497664)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_81_cast_fp16 = conv(dilations = var_81_dilations_0, groups = var_81_groups_0, pad = var_81_pad_0, pad_type = var_81_pad_type_0, strides = var_81_strides_0, weight = var_61_promoted_to_fp16, x = input_cast_fp16)[name = string("op_81_cast_fp16")];
+            tensor<int32, [1]> var_83_axes_0 = const()[name = string("op_83_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_83_cast_fp16 = squeeze(axes = var_83_axes_0, x = var_81_cast_fp16)[name = string("op_83_cast_fp16")];
+            tensor<int32, [3]> logits_5_perm_0 = const()[name = string("logits_5_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_107_pad_type_0 = const()[name = string("op_107_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_107_strides_0 = const()[name = string("op_107_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_107_pad_0 = const()[name = string("op_107_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_107_dilations_0 = const()[name = string("op_107_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_107_groups_0 = const()[name = string("op_107_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_87_promoted_to_fp16 = const()[name = string("op_87_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(113246464)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_107_cast_fp16 = conv(dilations = var_107_dilations_0, groups = var_107_groups_0, pad = var_107_pad_0, pad_type = var_107_pad_type_0, strides = var_107_strides_0, weight = var_87_promoted_to_fp16, x = input_cast_fp16)[name = string("op_107_cast_fp16")];
+            tensor<int32, [1]> var_109_axes_0 = const()[name = string("op_109_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_109_cast_fp16 = squeeze(axes = var_109_axes_0, x = var_107_cast_fp16)[name = string("op_109_cast_fp16")];
+            tensor<int32, [3]> logits_7_perm_0 = const()[name = string("logits_7_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_133_pad_type_0 = const()[name = string("op_133_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_133_strides_0 = const()[name = string("op_133_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_133_pad_0 = const()[name = string("op_133_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_133_dilations_0 = const()[name = string("op_133_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_133_groups_0 = const()[name = string("op_133_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_113_promoted_to_fp16 = const()[name = string("op_113_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(150995264)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_133_cast_fp16 = conv(dilations = var_133_dilations_0, groups = var_133_groups_0, pad = var_133_pad_0, pad_type = var_133_pad_type_0, strides = var_133_strides_0, weight = var_113_promoted_to_fp16, x = input_cast_fp16)[name = string("op_133_cast_fp16")];
+            tensor<int32, [1]> var_135_axes_0 = const()[name = string("op_135_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_135_cast_fp16 = squeeze(axes = var_135_axes_0, x = var_133_cast_fp16)[name = string("op_135_cast_fp16")];
+            tensor<int32, [3]> logits_9_perm_0 = const()[name = string("logits_9_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_159_pad_type_0 = const()[name = string("op_159_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_159_strides_0 = const()[name = string("op_159_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_159_pad_0 = const()[name = string("op_159_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_159_dilations_0 = const()[name = string("op_159_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_159_groups_0 = const()[name = string("op_159_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_139_promoted_to_fp16 = const()[name = string("op_139_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(188744064)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_159_cast_fp16 = conv(dilations = var_159_dilations_0, groups = var_159_groups_0, pad = var_159_pad_0, pad_type = var_159_pad_type_0, strides = var_159_strides_0, weight = var_139_promoted_to_fp16, x = input_cast_fp16)[name = string("op_159_cast_fp16")];
+            tensor<int32, [1]> var_161_axes_0 = const()[name = string("op_161_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_161_cast_fp16 = squeeze(axes = var_161_axes_0, x = var_159_cast_fp16)[name = string("op_161_cast_fp16")];
+            tensor<int32, [3]> logits_11_perm_0 = const()[name = string("logits_11_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_185_pad_type_0 = const()[name = string("op_185_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_185_strides_0 = const()[name = string("op_185_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_185_pad_0 = const()[name = string("op_185_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_185_dilations_0 = const()[name = string("op_185_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_185_groups_0 = const()[name = string("op_185_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_165_promoted_to_fp16 = const()[name = string("op_165_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(226492864)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_185_cast_fp16 = conv(dilations = var_185_dilations_0, groups = var_185_groups_0, pad = var_185_pad_0, pad_type = var_185_pad_type_0, strides = var_185_strides_0, weight = var_165_promoted_to_fp16, x = input_cast_fp16)[name = string("op_185_cast_fp16")];
+            tensor<int32, [1]> var_187_axes_0 = const()[name = string("op_187_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_187_cast_fp16 = squeeze(axes = var_187_axes_0, x = var_185_cast_fp16)[name = string("op_187_cast_fp16")];
+            tensor<int32, [3]> logits_13_perm_0 = const()[name = string("logits_13_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_211_pad_type_0 = const()[name = string("op_211_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_211_strides_0 = const()[name = string("op_211_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_211_pad_0 = const()[name = string("op_211_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_211_dilations_0 = const()[name = string("op_211_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_211_groups_0 = const()[name = string("op_211_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_191_promoted_to_fp16 = const()[name = string("op_191_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(264241664)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_211_cast_fp16 = conv(dilations = var_211_dilations_0, groups = var_211_groups_0, pad = var_211_pad_0, pad_type = var_211_pad_type_0, strides = var_211_strides_0, weight = var_191_promoted_to_fp16, x = input_cast_fp16)[name = string("op_211_cast_fp16")];
+            tensor<int32, [1]> var_213_axes_0 = const()[name = string("op_213_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_213_cast_fp16 = squeeze(axes = var_213_axes_0, x = var_211_cast_fp16)[name = string("op_213_cast_fp16")];
+            tensor<int32, [3]> logits_15_perm_0 = const()[name = string("logits_15_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_237_pad_type_0 = const()[name = string("op_237_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_237_strides_0 = const()[name = string("op_237_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_237_pad_0 = const()[name = string("op_237_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_237_dilations_0 = const()[name = string("op_237_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_237_groups_0 = const()[name = string("op_237_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_217_promoted_to_fp16 = const()[name = string("op_217_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(301990464)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_237_cast_fp16 = conv(dilations = var_237_dilations_0, groups = var_237_groups_0, pad = var_237_pad_0, pad_type = var_237_pad_type_0, strides = var_237_strides_0, weight = var_217_promoted_to_fp16, x = input_cast_fp16)[name = string("op_237_cast_fp16")];
+            tensor<int32, [1]> var_239_axes_0 = const()[name = string("op_239_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_239_cast_fp16 = squeeze(axes = var_239_axes_0, x = var_237_cast_fp16)[name = string("op_239_cast_fp16")];
+            tensor<int32, [3]> logits_17_perm_0 = const()[name = string("logits_17_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_263_pad_type_0 = const()[name = string("op_263_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_263_strides_0 = const()[name = string("op_263_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_263_pad_0 = const()[name = string("op_263_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_263_dilations_0 = const()[name = string("op_263_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_263_groups_0 = const()[name = string("op_263_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_243_promoted_to_fp16 = const()[name = string("op_243_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(339739264)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_263_cast_fp16 = conv(dilations = var_263_dilations_0, groups = var_263_groups_0, pad = var_263_pad_0, pad_type = var_263_pad_type_0, strides = var_263_strides_0, weight = var_243_promoted_to_fp16, x = input_cast_fp16)[name = string("op_263_cast_fp16")];
+            tensor<int32, [1]> var_265_axes_0 = const()[name = string("op_265_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_265_cast_fp16 = squeeze(axes = var_265_axes_0, x = var_263_cast_fp16)[name = string("op_265_cast_fp16")];
+            tensor<int32, [3]> logits_19_perm_0 = const()[name = string("logits_19_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_289_pad_type_0 = const()[name = string("op_289_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_289_strides_0 = const()[name = string("op_289_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_289_pad_0 = const()[name = string("op_289_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_289_dilations_0 = const()[name = string("op_289_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_289_groups_0 = const()[name = string("op_289_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_269_promoted_to_fp16 = const()[name = string("op_269_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(377488064)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_289_cast_fp16 = conv(dilations = var_289_dilations_0, groups = var_289_groups_0, pad = var_289_pad_0, pad_type = var_289_pad_type_0, strides = var_289_strides_0, weight = var_269_promoted_to_fp16, x = input_cast_fp16)[name = string("op_289_cast_fp16")];
+            tensor<int32, [1]> var_291_axes_0 = const()[name = string("op_291_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_291_cast_fp16 = squeeze(axes = var_291_axes_0, x = var_289_cast_fp16)[name = string("op_291_cast_fp16")];
+            tensor<int32, [3]> logits_21_perm_0 = const()[name = string("logits_21_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_315_pad_type_0 = const()[name = string("op_315_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_315_strides_0 = const()[name = string("op_315_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_315_pad_0 = const()[name = string("op_315_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_315_dilations_0 = const()[name = string("op_315_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_315_groups_0 = const()[name = string("op_315_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_295_promoted_to_fp16 = const()[name = string("op_295_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(415236864)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_315_cast_fp16 = conv(dilations = var_315_dilations_0, groups = var_315_groups_0, pad = var_315_pad_0, pad_type = var_315_pad_type_0, strides = var_315_strides_0, weight = var_295_promoted_to_fp16, x = input_cast_fp16)[name = string("op_315_cast_fp16")];
+            tensor<int32, [1]> var_317_axes_0 = const()[name = string("op_317_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_317_cast_fp16 = squeeze(axes = var_317_axes_0, x = var_315_cast_fp16)[name = string("op_317_cast_fp16")];
+            tensor<int32, [3]> logits_23_perm_0 = const()[name = string("logits_23_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_341_pad_type_0 = const()[name = string("op_341_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_341_strides_0 = const()[name = string("op_341_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_341_pad_0 = const()[name = string("op_341_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_341_dilations_0 = const()[name = string("op_341_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_341_groups_0 = const()[name = string("op_341_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_321_promoted_to_fp16 = const()[name = string("op_321_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(452985664)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_341_cast_fp16 = conv(dilations = var_341_dilations_0, groups = var_341_groups_0, pad = var_341_pad_0, pad_type = var_341_pad_type_0, strides = var_341_strides_0, weight = var_321_promoted_to_fp16, x = input_cast_fp16)[name = string("op_341_cast_fp16")];
+            tensor<int32, [1]> var_343_axes_0 = const()[name = string("op_343_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_343_cast_fp16 = squeeze(axes = var_343_axes_0, x = var_341_cast_fp16)[name = string("op_343_cast_fp16")];
+            tensor<int32, [3]> logits_25_perm_0 = const()[name = string("logits_25_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_367_pad_type_0 = const()[name = string("op_367_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_367_strides_0 = const()[name = string("op_367_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_367_pad_0 = const()[name = string("op_367_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_367_dilations_0 = const()[name = string("op_367_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_367_groups_0 = const()[name = string("op_367_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_347_promoted_to_fp16 = const()[name = string("op_347_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(490734464)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_367_cast_fp16 = conv(dilations = var_367_dilations_0, groups = var_367_groups_0, pad = var_367_pad_0, pad_type = var_367_pad_type_0, strides = var_367_strides_0, weight = var_347_promoted_to_fp16, x = input_cast_fp16)[name = string("op_367_cast_fp16")];
+            tensor<int32, [1]> var_369_axes_0 = const()[name = string("op_369_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_369_cast_fp16 = squeeze(axes = var_369_axes_0, x = var_367_cast_fp16)[name = string("op_369_cast_fp16")];
+            tensor<int32, [3]> logits_27_perm_0 = const()[name = string("logits_27_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_393_pad_type_0 = const()[name = string("op_393_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_393_strides_0 = const()[name = string("op_393_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_393_pad_0 = const()[name = string("op_393_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_393_dilations_0 = const()[name = string("op_393_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_393_groups_0 = const()[name = string("op_393_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_373_promoted_to_fp16 = const()[name = string("op_373_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(528483264)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_393_cast_fp16 = conv(dilations = var_393_dilations_0, groups = var_393_groups_0, pad = var_393_pad_0, pad_type = var_393_pad_type_0, strides = var_393_strides_0, weight = var_373_promoted_to_fp16, x = input_cast_fp16)[name = string("op_393_cast_fp16")];
+            tensor<int32, [1]> var_395_axes_0 = const()[name = string("op_395_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_395_cast_fp16 = squeeze(axes = var_395_axes_0, x = var_393_cast_fp16)[name = string("op_395_cast_fp16")];
+            tensor<int32, [3]> logits_29_perm_0 = const()[name = string("logits_29_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            string var_419_pad_type_0 = const()[name = string("op_419_pad_type_0"), val = string("valid")];
+            tensor<int32, [2]> var_419_strides_0 = const()[name = string("op_419_strides_0"), val = tensor<int32, [2]>([1, 1])];
+            tensor<int32, [4]> var_419_pad_0 = const()[name = string("op_419_pad_0"), val = tensor<int32, [4]>([0, 0, 0, 0])];
+            tensor<int32, [2]> var_419_dilations_0 = const()[name = string("op_419_dilations_0"), val = tensor<int32, [2]>([1, 1])];
+            int32 var_419_groups_0 = const()[name = string("op_419_groups_0"), val = int32(1)];
+            tensor<fp16, [16384, 1152, 1, 1]> var_399_promoted_to_fp16 = const()[name = string("op_399_promoted_to_fp16"), val = tensor<fp16, [16384, 1152, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(566232064)))];
+            tensor<fp16, [1, 16384, 1, 1]> var_419_cast_fp16 = conv(dilations = var_419_dilations_0, groups = var_419_groups_0, pad = var_419_pad_0, pad_type = var_419_pad_type_0, strides = var_419_strides_0, weight = var_399_promoted_to_fp16, x = input_cast_fp16)[name = string("op_419_cast_fp16")];
+            tensor<int32, [1]> var_421_axes_0 = const()[name = string("op_421_axes_0"), val = tensor<int32, [1]>([2])];
+            tensor<fp16, [1, 16384, 1]> var_421_cast_fp16 = squeeze(axes = var_421_axes_0, x = var_419_cast_fp16)[name = string("op_421_cast_fp16")];
+            tensor<int32, [3]> logits_perm_0 = const()[name = string("logits_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            int32 chunk_argmax_1_axis_0 = const()[name = string("chunk_argmax_1_axis_0"), val = int32(-1)];
+            bool chunk_argmax_1_keep_dims_0 = const()[name = string("chunk_argmax_1_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_1_output_dtype_0 = const()[name = string("chunk_argmax_1_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_1_cast_fp16 = transpose(perm = logits_1_perm_0, x = var_31_cast_fp16)[name = string("transpose_15")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_1_cast_fp16 = reduce_argmax(axis = chunk_argmax_1_axis_0, keep_dims = chunk_argmax_1_keep_dims_0, output_dtype = chunk_argmax_1_output_dtype_0, x = logits_1_cast_fp16)[name = string("chunk_argmax_1_cast_fp16")];
+            int32 var_428 = const()[name = string("op_428"), val = int32(-1)];
+            bool var_430_validate_indices_0 = const()[name = string("op_430_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_1_cast_fp16_to_uint16_dtype_0 = const()[name = string("chunk_argmax_1_cast_fp16_to_uint16_dtype_0"), val = string("uint16")];
+            tensor<uint16, [1, 1, 1]> chunk_argmax_1_cast_fp16_to_uint16 = cast(dtype = chunk_argmax_1_cast_fp16_to_uint16_dtype_0, x = chunk_argmax_1_cast_fp16)[name = string("cast_19")];
+            tensor<fp16, [1, 1, 1]> var_430_cast_fp16_cast_int16 = gather_along_axis(axis = var_428, indices = chunk_argmax_1_cast_fp16_to_uint16, validate_indices = var_430_validate_indices_0, x = logits_1_cast_fp16)[name = string("op_430_cast_fp16_cast_int16")];
+            int32 chunk_argmax_3_axis_0 = const()[name = string("chunk_argmax_3_axis_0"), val = int32(-1)];
+            bool chunk_argmax_3_keep_dims_0 = const()[name = string("chunk_argmax_3_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_3_output_dtype_0 = const()[name = string("chunk_argmax_3_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_3_cast_fp16 = transpose(perm = logits_3_perm_0, x = var_57_cast_fp16)[name = string("transpose_14")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_3_cast_fp16 = reduce_argmax(axis = chunk_argmax_3_axis_0, keep_dims = chunk_argmax_3_keep_dims_0, output_dtype = chunk_argmax_3_output_dtype_0, x = logits_3_cast_fp16)[name = string("chunk_argmax_3_cast_fp16")];
+            int32 var_439 = const()[name = string("op_439"), val = int32(-1)];
+            bool var_441_validate_indices_0 = const()[name = string("op_441_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_3_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_3_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_3_cast_fp16_to_int16 = cast(dtype = chunk_argmax_3_cast_fp16_to_int16_dtype_0, x = chunk_argmax_3_cast_fp16)[name = string("cast_18")];
+            tensor<fp16, [1, 1, 1]> var_441_cast_fp16_cast_int16 = gather_along_axis(axis = var_439, indices = chunk_argmax_3_cast_fp16_to_int16, validate_indices = var_441_validate_indices_0, x = logits_3_cast_fp16)[name = string("op_441_cast_fp16_cast_int16")];
+            int32 chunk_argmax_5_axis_0 = const()[name = string("chunk_argmax_5_axis_0"), val = int32(-1)];
+            bool chunk_argmax_5_keep_dims_0 = const()[name = string("chunk_argmax_5_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_5_output_dtype_0 = const()[name = string("chunk_argmax_5_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_5_cast_fp16 = transpose(perm = logits_5_perm_0, x = var_83_cast_fp16)[name = string("transpose_13")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_5_cast_fp16 = reduce_argmax(axis = chunk_argmax_5_axis_0, keep_dims = chunk_argmax_5_keep_dims_0, output_dtype = chunk_argmax_5_output_dtype_0, x = logits_5_cast_fp16)[name = string("chunk_argmax_5_cast_fp16")];
+            int32 var_450 = const()[name = string("op_450"), val = int32(-1)];
+            bool var_452_validate_indices_0 = const()[name = string("op_452_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_5_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_5_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_5_cast_fp16_to_int16 = cast(dtype = chunk_argmax_5_cast_fp16_to_int16_dtype_0, x = chunk_argmax_5_cast_fp16)[name = string("cast_17")];
+            tensor<fp16, [1, 1, 1]> var_452_cast_fp16_cast_int16 = gather_along_axis(axis = var_450, indices = chunk_argmax_5_cast_fp16_to_int16, validate_indices = var_452_validate_indices_0, x = logits_5_cast_fp16)[name = string("op_452_cast_fp16_cast_int16")];
+            int32 chunk_argmax_7_axis_0 = const()[name = string("chunk_argmax_7_axis_0"), val = int32(-1)];
+            bool chunk_argmax_7_keep_dims_0 = const()[name = string("chunk_argmax_7_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_7_output_dtype_0 = const()[name = string("chunk_argmax_7_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_7_cast_fp16 = transpose(perm = logits_7_perm_0, x = var_109_cast_fp16)[name = string("transpose_12")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_7_cast_fp16 = reduce_argmax(axis = chunk_argmax_7_axis_0, keep_dims = chunk_argmax_7_keep_dims_0, output_dtype = chunk_argmax_7_output_dtype_0, x = logits_7_cast_fp16)[name = string("chunk_argmax_7_cast_fp16")];
+            int32 var_461 = const()[name = string("op_461"), val = int32(-1)];
+            bool var_463_validate_indices_0 = const()[name = string("op_463_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_7_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_7_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_7_cast_fp16_to_int16 = cast(dtype = chunk_argmax_7_cast_fp16_to_int16_dtype_0, x = chunk_argmax_7_cast_fp16)[name = string("cast_16")];
+            tensor<fp16, [1, 1, 1]> var_463_cast_fp16_cast_int16 = gather_along_axis(axis = var_461, indices = chunk_argmax_7_cast_fp16_to_int16, validate_indices = var_463_validate_indices_0, x = logits_7_cast_fp16)[name = string("op_463_cast_fp16_cast_int16")];
+            int32 chunk_argmax_9_axis_0 = const()[name = string("chunk_argmax_9_axis_0"), val = int32(-1)];
+            bool chunk_argmax_9_keep_dims_0 = const()[name = string("chunk_argmax_9_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_9_output_dtype_0 = const()[name = string("chunk_argmax_9_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_9_cast_fp16 = transpose(perm = logits_9_perm_0, x = var_135_cast_fp16)[name = string("transpose_11")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_9_cast_fp16 = reduce_argmax(axis = chunk_argmax_9_axis_0, keep_dims = chunk_argmax_9_keep_dims_0, output_dtype = chunk_argmax_9_output_dtype_0, x = logits_9_cast_fp16)[name = string("chunk_argmax_9_cast_fp16")];
+            int32 var_472 = const()[name = string("op_472"), val = int32(-1)];
+            bool var_474_validate_indices_0 = const()[name = string("op_474_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_9_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_9_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_9_cast_fp16_to_int16 = cast(dtype = chunk_argmax_9_cast_fp16_to_int16_dtype_0, x = chunk_argmax_9_cast_fp16)[name = string("cast_15")];
+            tensor<fp16, [1, 1, 1]> var_474_cast_fp16_cast_int16 = gather_along_axis(axis = var_472, indices = chunk_argmax_9_cast_fp16_to_int16, validate_indices = var_474_validate_indices_0, x = logits_9_cast_fp16)[name = string("op_474_cast_fp16_cast_int16")];
+            int32 chunk_argmax_11_axis_0 = const()[name = string("chunk_argmax_11_axis_0"), val = int32(-1)];
+            bool chunk_argmax_11_keep_dims_0 = const()[name = string("chunk_argmax_11_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_11_output_dtype_0 = const()[name = string("chunk_argmax_11_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_11_cast_fp16 = transpose(perm = logits_11_perm_0, x = var_161_cast_fp16)[name = string("transpose_10")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_11_cast_fp16 = reduce_argmax(axis = chunk_argmax_11_axis_0, keep_dims = chunk_argmax_11_keep_dims_0, output_dtype = chunk_argmax_11_output_dtype_0, x = logits_11_cast_fp16)[name = string("chunk_argmax_11_cast_fp16")];
+            int32 var_483 = const()[name = string("op_483"), val = int32(-1)];
+            bool var_485_validate_indices_0 = const()[name = string("op_485_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_11_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_11_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_11_cast_fp16_to_int16 = cast(dtype = chunk_argmax_11_cast_fp16_to_int16_dtype_0, x = chunk_argmax_11_cast_fp16)[name = string("cast_14")];
+            tensor<fp16, [1, 1, 1]> var_485_cast_fp16_cast_int16 = gather_along_axis(axis = var_483, indices = chunk_argmax_11_cast_fp16_to_int16, validate_indices = var_485_validate_indices_0, x = logits_11_cast_fp16)[name = string("op_485_cast_fp16_cast_int16")];
+            int32 chunk_argmax_13_axis_0 = const()[name = string("chunk_argmax_13_axis_0"), val = int32(-1)];
+            bool chunk_argmax_13_keep_dims_0 = const()[name = string("chunk_argmax_13_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_13_output_dtype_0 = const()[name = string("chunk_argmax_13_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_13_cast_fp16 = transpose(perm = logits_13_perm_0, x = var_187_cast_fp16)[name = string("transpose_9")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_13_cast_fp16 = reduce_argmax(axis = chunk_argmax_13_axis_0, keep_dims = chunk_argmax_13_keep_dims_0, output_dtype = chunk_argmax_13_output_dtype_0, x = logits_13_cast_fp16)[name = string("chunk_argmax_13_cast_fp16")];
+            int32 var_494 = const()[name = string("op_494"), val = int32(-1)];
+            bool var_496_validate_indices_0 = const()[name = string("op_496_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_13_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_13_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_13_cast_fp16_to_int16 = cast(dtype = chunk_argmax_13_cast_fp16_to_int16_dtype_0, x = chunk_argmax_13_cast_fp16)[name = string("cast_13")];
+            tensor<fp16, [1, 1, 1]> var_496_cast_fp16_cast_int16 = gather_along_axis(axis = var_494, indices = chunk_argmax_13_cast_fp16_to_int16, validate_indices = var_496_validate_indices_0, x = logits_13_cast_fp16)[name = string("op_496_cast_fp16_cast_int16")];
+            int32 chunk_argmax_15_axis_0 = const()[name = string("chunk_argmax_15_axis_0"), val = int32(-1)];
+            bool chunk_argmax_15_keep_dims_0 = const()[name = string("chunk_argmax_15_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_15_output_dtype_0 = const()[name = string("chunk_argmax_15_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_15_cast_fp16 = transpose(perm = logits_15_perm_0, x = var_213_cast_fp16)[name = string("transpose_8")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_15_cast_fp16 = reduce_argmax(axis = chunk_argmax_15_axis_0, keep_dims = chunk_argmax_15_keep_dims_0, output_dtype = chunk_argmax_15_output_dtype_0, x = logits_15_cast_fp16)[name = string("chunk_argmax_15_cast_fp16")];
+            int32 var_505 = const()[name = string("op_505"), val = int32(-1)];
+            bool var_507_validate_indices_0 = const()[name = string("op_507_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_15_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_15_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_15_cast_fp16_to_int16 = cast(dtype = chunk_argmax_15_cast_fp16_to_int16_dtype_0, x = chunk_argmax_15_cast_fp16)[name = string("cast_12")];
+            tensor<fp16, [1, 1, 1]> var_507_cast_fp16_cast_int16 = gather_along_axis(axis = var_505, indices = chunk_argmax_15_cast_fp16_to_int16, validate_indices = var_507_validate_indices_0, x = logits_15_cast_fp16)[name = string("op_507_cast_fp16_cast_int16")];
+            int32 chunk_argmax_17_axis_0 = const()[name = string("chunk_argmax_17_axis_0"), val = int32(-1)];
+            bool chunk_argmax_17_keep_dims_0 = const()[name = string("chunk_argmax_17_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_17_output_dtype_0 = const()[name = string("chunk_argmax_17_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_17_cast_fp16 = transpose(perm = logits_17_perm_0, x = var_239_cast_fp16)[name = string("transpose_7")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_17_cast_fp16 = reduce_argmax(axis = chunk_argmax_17_axis_0, keep_dims = chunk_argmax_17_keep_dims_0, output_dtype = chunk_argmax_17_output_dtype_0, x = logits_17_cast_fp16)[name = string("chunk_argmax_17_cast_fp16")];
+            int32 var_516 = const()[name = string("op_516"), val = int32(-1)];
+            bool var_518_validate_indices_0 = const()[name = string("op_518_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_17_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_17_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_17_cast_fp16_to_int16 = cast(dtype = chunk_argmax_17_cast_fp16_to_int16_dtype_0, x = chunk_argmax_17_cast_fp16)[name = string("cast_11")];
+            tensor<fp16, [1, 1, 1]> var_518_cast_fp16_cast_int16 = gather_along_axis(axis = var_516, indices = chunk_argmax_17_cast_fp16_to_int16, validate_indices = var_518_validate_indices_0, x = logits_17_cast_fp16)[name = string("op_518_cast_fp16_cast_int16")];
+            int32 chunk_argmax_19_axis_0 = const()[name = string("chunk_argmax_19_axis_0"), val = int32(-1)];
+            bool chunk_argmax_19_keep_dims_0 = const()[name = string("chunk_argmax_19_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_19_output_dtype_0 = const()[name = string("chunk_argmax_19_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_19_cast_fp16 = transpose(perm = logits_19_perm_0, x = var_265_cast_fp16)[name = string("transpose_6")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_19_cast_fp16 = reduce_argmax(axis = chunk_argmax_19_axis_0, keep_dims = chunk_argmax_19_keep_dims_0, output_dtype = chunk_argmax_19_output_dtype_0, x = logits_19_cast_fp16)[name = string("chunk_argmax_19_cast_fp16")];
+            int32 var_527 = const()[name = string("op_527"), val = int32(-1)];
+            bool var_529_validate_indices_0 = const()[name = string("op_529_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_19_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_19_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_19_cast_fp16_to_int16 = cast(dtype = chunk_argmax_19_cast_fp16_to_int16_dtype_0, x = chunk_argmax_19_cast_fp16)[name = string("cast_10")];
+            tensor<fp16, [1, 1, 1]> var_529_cast_fp16_cast_int16 = gather_along_axis(axis = var_527, indices = chunk_argmax_19_cast_fp16_to_int16, validate_indices = var_529_validate_indices_0, x = logits_19_cast_fp16)[name = string("op_529_cast_fp16_cast_int16")];
+            int32 chunk_argmax_21_axis_0 = const()[name = string("chunk_argmax_21_axis_0"), val = int32(-1)];
+            bool chunk_argmax_21_keep_dims_0 = const()[name = string("chunk_argmax_21_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_21_output_dtype_0 = const()[name = string("chunk_argmax_21_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_21_cast_fp16 = transpose(perm = logits_21_perm_0, x = var_291_cast_fp16)[name = string("transpose_5")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_21_cast_fp16 = reduce_argmax(axis = chunk_argmax_21_axis_0, keep_dims = chunk_argmax_21_keep_dims_0, output_dtype = chunk_argmax_21_output_dtype_0, x = logits_21_cast_fp16)[name = string("chunk_argmax_21_cast_fp16")];
+            int32 var_538 = const()[name = string("op_538"), val = int32(-1)];
+            bool var_540_validate_indices_0 = const()[name = string("op_540_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_21_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_21_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_21_cast_fp16_to_int16 = cast(dtype = chunk_argmax_21_cast_fp16_to_int16_dtype_0, x = chunk_argmax_21_cast_fp16)[name = string("cast_9")];
+            tensor<fp16, [1, 1, 1]> var_540_cast_fp16_cast_int16 = gather_along_axis(axis = var_538, indices = chunk_argmax_21_cast_fp16_to_int16, validate_indices = var_540_validate_indices_0, x = logits_21_cast_fp16)[name = string("op_540_cast_fp16_cast_int16")];
+            int32 chunk_argmax_23_axis_0 = const()[name = string("chunk_argmax_23_axis_0"), val = int32(-1)];
+            bool chunk_argmax_23_keep_dims_0 = const()[name = string("chunk_argmax_23_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_23_output_dtype_0 = const()[name = string("chunk_argmax_23_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_23_cast_fp16 = transpose(perm = logits_23_perm_0, x = var_317_cast_fp16)[name = string("transpose_4")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_23_cast_fp16 = reduce_argmax(axis = chunk_argmax_23_axis_0, keep_dims = chunk_argmax_23_keep_dims_0, output_dtype = chunk_argmax_23_output_dtype_0, x = logits_23_cast_fp16)[name = string("chunk_argmax_23_cast_fp16")];
+            int32 var_549 = const()[name = string("op_549"), val = int32(-1)];
+            bool var_551_validate_indices_0 = const()[name = string("op_551_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_23_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_23_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_23_cast_fp16_to_int16 = cast(dtype = chunk_argmax_23_cast_fp16_to_int16_dtype_0, x = chunk_argmax_23_cast_fp16)[name = string("cast_8")];
+            tensor<fp16, [1, 1, 1]> var_551_cast_fp16_cast_int16 = gather_along_axis(axis = var_549, indices = chunk_argmax_23_cast_fp16_to_int16, validate_indices = var_551_validate_indices_0, x = logits_23_cast_fp16)[name = string("op_551_cast_fp16_cast_int16")];
+            int32 chunk_argmax_25_axis_0 = const()[name = string("chunk_argmax_25_axis_0"), val = int32(-1)];
+            bool chunk_argmax_25_keep_dims_0 = const()[name = string("chunk_argmax_25_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_25_output_dtype_0 = const()[name = string("chunk_argmax_25_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_25_cast_fp16 = transpose(perm = logits_25_perm_0, x = var_343_cast_fp16)[name = string("transpose_3")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_25_cast_fp16 = reduce_argmax(axis = chunk_argmax_25_axis_0, keep_dims = chunk_argmax_25_keep_dims_0, output_dtype = chunk_argmax_25_output_dtype_0, x = logits_25_cast_fp16)[name = string("chunk_argmax_25_cast_fp16")];
+            int32 var_560 = const()[name = string("op_560"), val = int32(-1)];
+            bool var_562_validate_indices_0 = const()[name = string("op_562_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_25_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_25_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_25_cast_fp16_to_int16 = cast(dtype = chunk_argmax_25_cast_fp16_to_int16_dtype_0, x = chunk_argmax_25_cast_fp16)[name = string("cast_7")];
+            tensor<fp16, [1, 1, 1]> var_562_cast_fp16_cast_int16 = gather_along_axis(axis = var_560, indices = chunk_argmax_25_cast_fp16_to_int16, validate_indices = var_562_validate_indices_0, x = logits_25_cast_fp16)[name = string("op_562_cast_fp16_cast_int16")];
+            int32 chunk_argmax_27_axis_0 = const()[name = string("chunk_argmax_27_axis_0"), val = int32(-1)];
+            bool chunk_argmax_27_keep_dims_0 = const()[name = string("chunk_argmax_27_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_27_output_dtype_0 = const()[name = string("chunk_argmax_27_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_27_cast_fp16 = transpose(perm = logits_27_perm_0, x = var_369_cast_fp16)[name = string("transpose_2")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_27_cast_fp16 = reduce_argmax(axis = chunk_argmax_27_axis_0, keep_dims = chunk_argmax_27_keep_dims_0, output_dtype = chunk_argmax_27_output_dtype_0, x = logits_27_cast_fp16)[name = string("chunk_argmax_27_cast_fp16")];
+            int32 var_571 = const()[name = string("op_571"), val = int32(-1)];
+            bool var_573_validate_indices_0 = const()[name = string("op_573_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_27_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_27_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_27_cast_fp16_to_int16 = cast(dtype = chunk_argmax_27_cast_fp16_to_int16_dtype_0, x = chunk_argmax_27_cast_fp16)[name = string("cast_6")];
+            tensor<fp16, [1, 1, 1]> var_573_cast_fp16_cast_int16 = gather_along_axis(axis = var_571, indices = chunk_argmax_27_cast_fp16_to_int16, validate_indices = var_573_validate_indices_0, x = logits_27_cast_fp16)[name = string("op_573_cast_fp16_cast_int16")];
+            int32 chunk_argmax_29_axis_0 = const()[name = string("chunk_argmax_29_axis_0"), val = int32(-1)];
+            bool chunk_argmax_29_keep_dims_0 = const()[name = string("chunk_argmax_29_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_29_output_dtype_0 = const()[name = string("chunk_argmax_29_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_29_cast_fp16 = transpose(perm = logits_29_perm_0, x = var_395_cast_fp16)[name = string("transpose_1")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_29_cast_fp16 = reduce_argmax(axis = chunk_argmax_29_axis_0, keep_dims = chunk_argmax_29_keep_dims_0, output_dtype = chunk_argmax_29_output_dtype_0, x = logits_29_cast_fp16)[name = string("chunk_argmax_29_cast_fp16")];
+            int32 var_582 = const()[name = string("op_582"), val = int32(-1)];
+            bool var_584_validate_indices_0 = const()[name = string("op_584_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_29_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_29_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_29_cast_fp16_to_int16 = cast(dtype = chunk_argmax_29_cast_fp16_to_int16_dtype_0, x = chunk_argmax_29_cast_fp16)[name = string("cast_5")];
+            tensor<fp16, [1, 1, 1]> var_584_cast_fp16_cast_int16 = gather_along_axis(axis = var_582, indices = chunk_argmax_29_cast_fp16_to_int16, validate_indices = var_584_validate_indices_0, x = logits_29_cast_fp16)[name = string("op_584_cast_fp16_cast_int16")];
+            int32 chunk_argmax_axis_0 = const()[name = string("chunk_argmax_axis_0"), val = int32(-1)];
+            bool chunk_argmax_keep_dims_0 = const()[name = string("chunk_argmax_keep_dims_0"), val = bool(true)];
+            string chunk_argmax_output_dtype_0 = const()[name = string("chunk_argmax_output_dtype_0"), val = string("int32")];
+            tensor<fp16, [1, 1, 16384]> logits_cast_fp16 = transpose(perm = logits_perm_0, x = var_421_cast_fp16)[name = string("transpose_0")];
+            tensor<int32, [1, 1, 1]> chunk_argmax_cast_fp16 = reduce_argmax(axis = chunk_argmax_axis_0, keep_dims = chunk_argmax_keep_dims_0, output_dtype = chunk_argmax_output_dtype_0, x = logits_cast_fp16)[name = string("chunk_argmax_cast_fp16")];
+            int32 var_593 = const()[name = string("op_593"), val = int32(-1)];
+            bool chunk_max_val_validate_indices_0 = const()[name = string("chunk_max_val_validate_indices_0"), val = bool(false)];
+            string chunk_argmax_cast_fp16_to_int16_dtype_0 = const()[name = string("chunk_argmax_cast_fp16_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 1]> chunk_argmax_cast_fp16_to_int16 = cast(dtype = chunk_argmax_cast_fp16_to_int16_dtype_0, x = chunk_argmax_cast_fp16)[name = string("cast_4")];
+            tensor<fp16, [1, 1, 1]> chunk_max_val_cast_fp16_cast_int16 = gather_along_axis(axis = var_593, indices = chunk_argmax_cast_fp16_to_int16, validate_indices = chunk_max_val_validate_indices_0, x = logits_cast_fp16)[name = string("chunk_max_val_cast_fp16_cast_int16")];
+            int32 var_602 = const()[name = string("op_602"), val = int32(-1)];
+            bool var_603_interleave_0 = const()[name = string("op_603_interleave_0"), val = bool(false)];
+            tensor<int32, [1, 1, 16]> var_603 = concat(axis = var_602, interleave = var_603_interleave_0, values = (chunk_argmax_1_cast_fp16, chunk_argmax_3_cast_fp16, chunk_argmax_5_cast_fp16, chunk_argmax_7_cast_fp16, chunk_argmax_9_cast_fp16, chunk_argmax_11_cast_fp16, chunk_argmax_13_cast_fp16, chunk_argmax_15_cast_fp16, chunk_argmax_17_cast_fp16, chunk_argmax_19_cast_fp16, chunk_argmax_21_cast_fp16, chunk_argmax_23_cast_fp16, chunk_argmax_25_cast_fp16, chunk_argmax_27_cast_fp16, chunk_argmax_29_cast_fp16, chunk_argmax_cast_fp16))[name = string("op_603")];
+            tensor<int32, [1]> var_605_axes_0 = const()[name = string("op_605_axes_0"), val = tensor<int32, [1]>([0])];
+            string var_603_to_int16_dtype_0 = const()[name = string("op_603_to_int16_dtype_0"), val = string("int16")];
+            tensor<int16, [1, 1, 16]> var_603_to_int16 = cast(dtype = var_603_to_int16_dtype_0, x = var_603)[name = string("cast_3")];
+            tensor<int16, [1, 16]> var_605_cast_uint16 = squeeze(axes = var_605_axes_0, x = var_603_to_int16)[name = string("op_605_cast_uint16")];
+            tensor<int32, [1]> var_607_axes_0 = const()[name = string("op_607_axes_0"), val = tensor<int32, [1]>([0])];
+            tensor<int16, [16]> var_607_cast_uint16 = squeeze(axes = var_607_axes_0, x = var_605_cast_uint16)[name = string("op_607_cast_uint16")];
+            string var_607_cast_uint16_to_int32_dtype_0 = const()[name = string("op_607_cast_uint16_to_int32_dtype_0"), val = string("int32")];
+            int32 var_609 = const()[name = string("op_609"), val = int32(-1)];
+            bool var_610_interleave_0 = const()[name = string("op_610_interleave_0"), val = bool(false)];
+            tensor<fp16, [1, 1, 16]> var_610_cast_fp16 = concat(axis = var_609, interleave = var_610_interleave_0, values = (var_430_cast_fp16_cast_int16, var_441_cast_fp16_cast_int16, var_452_cast_fp16_cast_int16, var_463_cast_fp16_cast_int16, var_474_cast_fp16_cast_int16, var_485_cast_fp16_cast_int16, var_496_cast_fp16_cast_int16, var_507_cast_fp16_cast_int16, var_518_cast_fp16_cast_int16, var_529_cast_fp16_cast_int16, var_540_cast_fp16_cast_int16, var_551_cast_fp16_cast_int16, var_562_cast_fp16_cast_int16, var_573_cast_fp16_cast_int16, var_584_cast_fp16_cast_int16, chunk_max_val_cast_fp16_cast_int16))[name = string("op_610_cast_fp16")];
+            tensor<int32, [1]> var_612_axes_0 = const()[name = string("op_612_axes_0"), val = tensor<int32, [1]>([0])];
+            tensor<fp16, [1, 16]> var_612_cast_fp16 = squeeze(axes = var_612_axes_0, x = var_610_cast_fp16)[name = string("op_612_cast_fp16")];
+            tensor<int32, [1]> var_614_axes_0 = const()[name = string("op_614_axes_0"), val = tensor<int32, [1]>([0])];
+            tensor<fp16, [16]> argmax_val = squeeze(axes = var_614_axes_0, x = var_612_cast_fp16)[name = string("op_614_cast_fp16")];
+            tensor<int32, [16]> argmax_idx = cast(dtype = var_607_cast_uint16_to_int32_dtype_0, x = var_607_cast_uint16)[name = string("cast_2")];
+        } -> (argmax_idx, argmax_val);
+}

gemma3_lm_head.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7062d8f702fc39d97d87deb03ec07bef12e3d0668c909eb5bc629e27c370de81
+size 603980864

meta.yaml

@@ -0,0 +1,29 @@
+model_info:
+  name: anemll-google-gemma-3-1b-it-ctx512
+  version: 0.3.5
+  description: |
+    Demonstarates running google-gemma-3-1b-it on Apple Neural Engine
+    Context length: 512
+    Batch size: 64
+    Chunks: 2
+  license: MIT
+  author: Anemll
+  framework: Core ML
+  language: Python
+  architecture: gemma3_text
+  parameters:
+    context_length: 512
+    batch_size: 64
+    lut_embeddings: none
+    lut_ffn: none
+    lut_lmhead: none
+    num_chunks: 2
+    model_prefix: gemma3
+    embeddings: gemma3_embeddings.mlmodelc
+    lm_head: gemma3_lm_head.mlmodelc
+    ffn: gemma3_FFN_PF_chunk_01of02.mlmodelc
+    split_lm_head: 16
+    argmax_in_model: true
+    sliding_window: 512
+    prefill_dynamic_slice: true
+    single_cache: true

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074