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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,4 @@
+{
+  "tokenizer_class": "Qwen2Tokenizer",
+  "model_type": "qwen3"
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

meta.yaml

@@ -0,0 +1,54 @@
+model_info:
+  name: anemll-SLM-SQL-0.6B-ctx4096
+  version: 0.3.5
+  description: |
+    Demonstarates running SLM-SQL-0.6B on Apple Neural Engine
+    Context length: 4096
+    Batch size: 64
+    Chunks: 1
+  license: MIT
+  author: Anemll
+  framework: Core ML
+  language: Python
+  architecture: qwen3
+  parameters:
+    context_length: 4096
+    batch_size: 64
+    lut_embeddings: none
+    lut_ffn: 6
+    lut_lmhead: 6
+    num_chunks: 1
+    model_prefix: qwen
+    embeddings: qwen_embeddings.mlmodelc
+    lm_head: qwen_lm_head_lut6.mlmodelc
+    ffn: qwen_FFN_PF_lut6_chunk_01of01.mlmodelc
+    split_lm_head: 16
+    vocab_size: 151936
+    lm_head_chunk_sizes: [9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496]
+    prefill_dynamic_slice: true
+
+# =============================================================================
+# Conversion Parameters (for troubleshooting)
+# =============================================================================
+# Generated: 2026-03-15 08:43:31
+#
+# model_path: /tmp/ios_models/downloads/SLM-SQL-0.6B
+# output_dir: /tmp/ios_models/SLM-SQL-0.6B-ctx4096
+# command_line: ./anemll/utils/convert_model.sh --model /tmp/ios_models/downloads/SLM-SQL-0.6B --output /tmp/ios_models/SLM-SQL-0.6B-ctx4096 --context 4096 --batch 64 --chunk 1 --lut2 6 --lut3 6
+# context_length: 4096
+# batch_size: 64
+# num_chunks: 1
+# lut_part1: none
+# lut_part2: 6
+# lut_part3: 6
+# prefix: qwen
+# architecture: qwen3
+# argmax_in_model: false
+# split_rotate: false
+# single_cache: false
+# dynamic_prefill_slice: true
+# monolithic: false
+# anemll_version: 0.3.5
+# vocab_size: 151936
+# lm_head_chunk_sizes: "[9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496, 9496]"
+# =============================================================================

qwen_FFN_PF_lut6_chunk_01of01.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a029f537a394ae673a6621fcf0d8832d47f5926e4380bb09ce80e77f164bc9c
+size 243

qwen_FFN_PF_lut6_chunk_01of01.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d47b89847bc26c0f884181ddb231d65ae4c3584883668eb922cc5bc8a8b3fd8
+size 981

qwen_FFN_PF_lut6_chunk_01of01.mlmodelc/metadata.json

@@ -0,0 +1,321 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "userDefinedMetadata" : {
+      "com.anemll.lut_bits" : "6",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.anemll.context_length" : "4096",
+      "com.anemll.num_chunks" : "1",
+      "com.anemll.batch_size" : "64",
+      "com.anemll.info" : "Converted with Anemll v0.1.1",
+      "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 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1024]",
+        "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 × 4096)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 4096]",
+        "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 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1024]",
+        "name" : "output_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "storagePrecision" : "Mixed (Float16, Palettized (13 bits), Palettized (14 bits), Palettized (15 bits), UInt6)",
+    "method" : "predict",
+    "functions" : [
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1024]",
+            "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 × 4096)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1, 4096]",
+            "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" : "Mixed (Float16, Palettized (13 bits), Palettized (14 bits), Palettized (15 bits), UInt6)",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 56 × 8 × 4096 × 128)",
+            "shortDescription" : "",
+            "shape" : "[56, 8, 4096, 128]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1024]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "infer",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.expandDims" : 112,
+          "Ios18.mul" : 450,
+          "Ios18.softmax" : 28,
+          "Ios18.matmul" : 56,
+          "Identity" : 1,
+          "Ios18.greaterEqual" : 2,
+          "Select" : 2,
+          "Ios18.readState" : 57,
+          "Tile" : 56,
+          "Ios18.gather" : 2,
+          "Ios18.add" : 143,
+          "Ios18.layerNorm" : 113,
+          "Ios18.sliceUpdate" : 56,
+          "Ios18.writeState" : 56,
+          "Ios18.reshape" : 170,
+          "Ios18.constexprLutToDense" : 196,
+          "Ios18.conv" : 196,
+          "Ios18.concat" : 281,
+          "Ios18.transpose" : 168,
+          "Ios18.cast" : 5,
+          "Ios18.silu" : 28,
+          "Ios18.sliceByIndex" : 281,
+          "Ios18.squeeze" : 84
+        }
+      },
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 64 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 64, 1024]",
+            "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 × 4096)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 64, 4096]",
+            "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" : "Mixed (Float16, Palettized (13 bits), Palettized (14 bits), Palettized (15 bits), UInt6)",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 56 × 8 × 4096 × 128)",
+            "shortDescription" : "",
+            "shape" : "[56, 8, 4096, 128]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1024]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "prefill",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.expandDims" : 112,
+          "Ios18.mul" : 448,
+          "Ios18.softmax" : 28,
+          "Ios18.matmul" : 56,
+          "Ios18.greaterEqual" : 2,
+          "Select" : 2,
+          "Ios18.readState" : 57,
+          "Tile" : 56,
+          "Ios18.gather" : 2,
+          "Ios18.add" : 143,
+          "Ios18.layerNorm" : 112,
+          "Ios18.sliceUpdate" : 56,
+          "Ios18.writeState" : 56,
+          "Ios18.reshape" : 226,
+          "Ios18.constexprLutToDense" : 196,
+          "Ios18.conv" : 196,
+          "Ios18.concat" : 280,
+          "Ios18.transpose" : 254,
+          "Ios18.cast" : 5,
+          "Ios18.silu" : 28,
+          "Ios18.sliceByIndex" : 281,
+          "Ios18.squeeze" : 84
+        }
+      }
+    ],
+    "version" : "0.1.1",
+    "isUpdatable" : "0",
+    "defaultFunctionName" : "infer",
+    "specificationVersion" : 9,
+    "stateSchema" : [
+      {
+        "dataType" : "Float16",
+        "isOptional" : "0",
+        "formattedType" : "State (Float16 56 × 8 × 4096 × 128)",
+        "shortDescription" : "",
+        "shape" : "[56, 8, 4096, 128]",
+        "name" : "model_model_kv_cache_0",
+        "type" : "State"
+      }
+    ],
+    "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 112,
+      "Ios18.mul" : 450,
+      "Ios18.softmax" : 28,
+      "Ios18.matmul" : 56,
+      "Identity" : 1,
+      "Ios18.greaterEqual" : 2,
+      "Select" : 2,
+      "Ios18.readState" : 57,
+      "Tile" : 56,
+      "Ios18.gather" : 2,
+      "Ios18.add" : 143,
+      "Ios18.layerNorm" : 113,
+      "Ios18.sliceUpdate" : 56,
+      "Ios18.writeState" : 56,
+      "Ios18.reshape" : 170,
+      "Ios18.constexprLutToDense" : 196,
+      "Ios18.conv" : 196,
+      "Ios18.concat" : 281,
+      "Ios18.transpose" : 168,
+      "Ios18.cast" : 5,
+      "Ios18.silu" : 28,
+      "Ios18.sliceByIndex" : 281,
+      "Ios18.squeeze" : 84
+    },
+    "shortDescription" : "Anemll Model: Multifunction FFN+Prefill",
+    "generatedClassName" : "qwen_FFN_PF_lut6_chunk_01of01",
+    "author" : "Converted with Anemll v0.1.1",
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    }
+  }
+]

qwen_FFN_PF_lut6_chunk_01of01.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8faf1787fb3ef8398cad0d18e7373e133936f2b1aa1634f81108bc4535421c78
+size 340164352

qwen_embeddings.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0da21dd679ed8ca075f439f0815d93426cb3cd811ad01625e4adadb1e9558f
+size 243

qwen_embeddings.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e6775ccdc7970ad9c4f25e6d635aae8efda93bab015547e407f4ff6b2f7fac
+size 560

qwen_embeddings.mlmodelc/metadata.json

@@ -0,0 +1,71 @@
+[
+  {
+    "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" : "0.1.1",
+    "modelParameters" : [
+
+    ],
+    "author" : "Converted with Anemll v0.1.1",
+    "specificationVersion" : 9,
+    "storagePrecision" : "Float16",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.greaterEqual" : 1,
+      "Ios18.add" : 1,
+      "Select" : 1,
+      "Ios18.gather" : 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.conversion_date" : "2026-03-15",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.anemll.info" : "Converted with Anemll v0.1.1",
+      "com.anemll.context_length" : "4096"
+    },
+    "generatedClassName" : "qwen_embeddings",
+    "method" : "predict"
+  }
+]

qwen_embeddings.mlmodelc/model.mil

@@ -0,0 +1,16 @@
+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]}}}})))] {
+            int32 hidden_states_batch_dims_0 = const()[name = string("hidden_states_batch_dims_0"), val = int32(0)];
+            bool hidden_states_validate_indices_0 = const()[name = string("hidden_states_validate_indices_0"), val = bool(false)];
+            tensor<fp16, [151936, 1024]> embed_tokens_weight_to_fp16 = const()[name = string("embed_tokens_weight_to_fp16"), val = tensor<fp16, [151936, 1024]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64)))];
+            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(151936)];
+            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_cast_fp16_axis_0 = const()[name = string("hidden_states_cast_fp16_axis_0"), val = int32(0)];
+            tensor<fp16, [1, ?, 1024]> hidden_states = gather(axis = hidden_states_cast_fp16_axis_0, batch_dims = hidden_states_batch_dims_0, indices = select_0, validate_indices = hidden_states_validate_indices_0, x = embed_tokens_weight_to_fp16)[name = string("hidden_states_cast_fp16")];
+        } -> (hidden_states);
+}

qwen_embeddings.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c0827d84c182c810e7a2e95ee9ac4777554b59b321d0679284f25528451dfc
+size 311165056

qwen_lm_head_lut6.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc555da9cae94c617b6e37e54be86610cc094424bcc390b646c10bff8b04426
+size 243

qwen_lm_head_lut6.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f834f165ba7554371237a4cf13a1112d9f630572917a71a7cf1a94f7506c53d
+size 1107

qwen_lm_head_lut6.mlmodelc/metadata.json

@@ -0,0 +1,223 @@
+[
+  {
+    "shortDescription" : "Anemll Model (LM Head) converted to CoreML",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits2",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits3",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits4",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits5",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits6",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits7",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits8",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits9",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits10",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits11",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits12",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits13",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits14",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits15",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits16",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "0.1.1",
+    "modelParameters" : [
+
+    ],
+    "author" : "Converted with Anemll v0.1.1",
+    "specificationVersion" : 9,
+    "storagePrecision" : "Mixed (Float16, Palettized (17 bits), UInt6)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.transpose" : 17,
+      "Ios18.constexprLutToDense" : 16,
+      "Ios18.expandDims" : 1,
+      "Ios18.conv" : 16,
+      "Ios18.squeeze" : 16
+    },
+    "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" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1024]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.source" : "torch==2.5.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.github.apple.coremltools.conversion_date" : "2026-03-15",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.anemll.context_length" : "4096",
+      "com.anemll.lm_head_chunk_sizes" : "9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496",
+      "com.anemll.vocab_size" : "151936",
+      "com.anemll.info" : "Converted with Anemll v0.1.1",
+      "com.anemll.lut_bits" : "6"
+    },
+    "generatedClassName" : "qwen_lm_head_lut6",
+    "method" : "predict"
+  }
+]

qwen_lm_head_lut6.mlmodelc/model.mil

@@ -0,0 +1,186 @@
+program(1.3)
+[buildInfo = dict<string, string>({{"coremlc-component-MIL", "3510.2.1"}, {"coremlc-version", "3500.32.1"}})]
+{
+    func main<ios18>(tensor<fp16, [1, 1, 1024]> 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, 1024, 1]> var_6_cast_fp16 = transpose(perm = var_5, x = hidden_states)[name = string("transpose_16")];
+            tensor<fp16, [1, 1024, 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, [9496, 1024, 1, 1]> op_9_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(64))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7293056))))[name = string("op_9_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_9_promoted_to_fp16_palettized, 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, 9496, 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]> var_34_perm_0 = const()[name = string("op_34_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, [9496, 1024, 1, 1]> op_35_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(7445056))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(14738048))))[name = string("op_35_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_35_promoted_to_fp16_palettized, 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, 9496, 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]> var_60_perm_0 = const()[name = string("op_60_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, [9496, 1024, 1, 1]> op_61_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(14890048))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(22183040))))[name = string("op_61_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_61_promoted_to_fp16_palettized, 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, 9496, 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]> var_86_perm_0 = const()[name = string("op_86_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, [9496, 1024, 1, 1]> op_87_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(22335040))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(29628032))))[name = string("op_87_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_87_promoted_to_fp16_palettized, 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, 9496, 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]> var_112_perm_0 = const()[name = string("op_112_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, [9496, 1024, 1, 1]> op_113_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(29780032))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(37073024))))[name = string("op_113_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_113_promoted_to_fp16_palettized, 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, 9496, 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]> var_138_perm_0 = const()[name = string("op_138_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, [9496, 1024, 1, 1]> op_139_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(37225024))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(44518016))))[name = string("op_139_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_139_promoted_to_fp16_palettized, 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, 9496, 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]> var_164_perm_0 = const()[name = string("op_164_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, [9496, 1024, 1, 1]> op_165_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(44670016))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(51963008))))[name = string("op_165_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_165_promoted_to_fp16_palettized, 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, 9496, 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]> var_190_perm_0 = const()[name = string("op_190_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, [9496, 1024, 1, 1]> op_191_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(52115008))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(59408000))))[name = string("op_191_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_191_promoted_to_fp16_palettized, 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, 9496, 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]> var_216_perm_0 = const()[name = string("op_216_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, [9496, 1024, 1, 1]> op_217_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(59560000))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(66852992))))[name = string("op_217_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_217_promoted_to_fp16_palettized, 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, 9496, 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]> var_242_perm_0 = const()[name = string("op_242_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, [9496, 1024, 1, 1]> op_243_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(67004992))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(74297984))))[name = string("op_243_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_243_promoted_to_fp16_palettized, 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, 9496, 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]> var_268_perm_0 = const()[name = string("op_268_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, [9496, 1024, 1, 1]> op_269_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(74449984))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(81742976))))[name = string("op_269_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_269_promoted_to_fp16_palettized, 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, 9496, 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]> var_294_perm_0 = const()[name = string("op_294_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, [9496, 1024, 1, 1]> op_295_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(81894976))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(89187968))))[name = string("op_295_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_295_promoted_to_fp16_palettized, 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, 9496, 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]> var_320_perm_0 = const()[name = string("op_320_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, [9496, 1024, 1, 1]> op_321_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(89339968))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(96632960))))[name = string("op_321_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_321_promoted_to_fp16_palettized, 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, 9496, 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]> var_346_perm_0 = const()[name = string("op_346_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, [9496, 1024, 1, 1]> op_347_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(96784960))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(104077952))))[name = string("op_347_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_347_promoted_to_fp16_palettized, 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, 9496, 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]> var_372_perm_0 = const()[name = string("op_372_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, [9496, 1024, 1, 1]> op_373_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(104229952))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(111522944))))[name = string("op_373_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_373_promoted_to_fp16_palettized, 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, 9496, 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]> var_398_perm_0 = const()[name = string("op_398_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, [9496, 1024, 1, 1]> op_399_promoted_to_fp16_palettized = constexpr_lut_to_dense(indices = tensor<uint6, [9496, 1024, 1, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(111674944))), lut = tensor<fp16, [1187, 1, 1, 1, 64, 1]>(BLOBFILE(path = string("@model_path/weights/weight.bin"), offset = uint64(118967936))))[name = string("op_399_promoted_to_fp16_palettized")];
+            tensor<fp16, [1, 9496, 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 = op_399_promoted_to_fp16_palettized, 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, 9496, 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]> var_424_perm_0 = const()[name = string("op_424_perm_0"), val = tensor<int32, [3]>([0, 2, 1])];
+            tensor<fp16, [1, 1, 9496]> logits1 = transpose(perm = var_34_perm_0, x = var_31_cast_fp16)[name = string("transpose_0")];
+            tensor<fp16, [1, 1, 9496]> logits2 = transpose(perm = var_60_perm_0, x = var_57_cast_fp16)[name = string("transpose_1")];
+            tensor<fp16, [1, 1, 9496]> logits3 = transpose(perm = var_86_perm_0, x = var_83_cast_fp16)[name = string("transpose_2")];
+            tensor<fp16, [1, 1, 9496]> logits4 = transpose(perm = var_112_perm_0, x = var_109_cast_fp16)[name = string("transpose_3")];
+            tensor<fp16, [1, 1, 9496]> logits5 = transpose(perm = var_138_perm_0, x = var_135_cast_fp16)[name = string("transpose_4")];
+            tensor<fp16, [1, 1, 9496]> logits6 = transpose(perm = var_164_perm_0, x = var_161_cast_fp16)[name = string("transpose_5")];
+            tensor<fp16, [1, 1, 9496]> logits7 = transpose(perm = var_190_perm_0, x = var_187_cast_fp16)[name = string("transpose_6")];
+            tensor<fp16, [1, 1, 9496]> logits8 = transpose(perm = var_216_perm_0, x = var_213_cast_fp16)[name = string("transpose_7")];
+            tensor<fp16, [1, 1, 9496]> logits9 = transpose(perm = var_242_perm_0, x = var_239_cast_fp16)[name = string("transpose_8")];
+            tensor<fp16, [1, 1, 9496]> logits10 = transpose(perm = var_268_perm_0, x = var_265_cast_fp16)[name = string("transpose_9")];
+            tensor<fp16, [1, 1, 9496]> logits11 = transpose(perm = var_294_perm_0, x = var_291_cast_fp16)[name = string("transpose_10")];
+            tensor<fp16, [1, 1, 9496]> logits12 = transpose(perm = var_320_perm_0, x = var_317_cast_fp16)[name = string("transpose_11")];
+            tensor<fp16, [1, 1, 9496]> logits13 = transpose(perm = var_346_perm_0, x = var_343_cast_fp16)[name = string("transpose_12")];
+            tensor<fp16, [1, 1, 9496]> logits14 = transpose(perm = var_372_perm_0, x = var_369_cast_fp16)[name = string("transpose_13")];
+            tensor<fp16, [1, 1, 9496]> logits15 = transpose(perm = var_398_perm_0, x = var_395_cast_fp16)[name = string("transpose_14")];
+            tensor<fp16, [1, 1, 9496]> logits16 = transpose(perm = var_424_perm_0, x = var_421_cast_fp16)[name = string("transpose_15")];
+        } -> (logits1, logits2, logits3, logits4, logits5, logits6, logits7, logits8, logits9, logits10, logits11, logits12, logits13, logits14, logits15, logits16);
+}

qwen_lm_head_lut6.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4881895c99cfb8964ba9a1c76d1b7543ad9de526eee330d203e595b0adcb5da9
+size 119119936

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
+size 11422821

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}