Duplicate from mlboydaisuke/gemma-4-E2B-coreml

Co-authored-by: Majima <mlboydaisuke@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,44 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+hf_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/swa/chunk1.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/swa/chunk2.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/swa/chunk3.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/swa/chunk4.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/prefill/prefill_chunk1.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/prefill/prefill_chunk2.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/prefill/prefill_chunk3.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text
+sdpa-8k/prefill/prefill_chunk4.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,176 @@
+---
+license: gemma
+library_name: coreml
+base_model: google/gemma-4-E2B-it
+tags:
+  - coreml
+  - apple-silicon
+  - ane
+  - on-device
+  - gemma-4
+  - gemma-3n
+  - multimodal
+  - vision
+  - audio
+pipeline_tag: image-text-to-text
+---
+
+## Use it from Swift
+
+<!-- swift-usage-begin -->
+### Add the package
+
+`Package.swift`:
+
+```swift
+.package(url: "https://github.com/john-rocky/CoreML-LLM", branch: "main"),
+
+// In your target:
+.product(name: "CoreMLLLM", package: "CoreML-LLM"),
+```
+
+Platforms: iOS 18+ / macOS 15+.
+
+### Download + chat (one call)
+
+```swift
+import CoreMLLLM
+
+let llm = try await CoreMLLLM.load(repo: "mlboydaisuke/gemma-4-E2B-coreml")
+
+let stream = try await llm.generate(
+    [CoreMLLLM.Message(role: .user, content: "Hello!")],
+    maxTokens: 256
+)
+for await chunk in stream { print(chunk, terminator: "") }
+```
+
+### Image / video / audio
+
+```swift
+// Image
+let stream = try await llm.generate(
+    [CoreMLLLM.Message(role: .user,
+                       content: "Describe this image")],
+    image: cgImage)
+
+// Video (frames + audio extracted internally)
+let stream = try await llm.generate(
+    [CoreMLLLM.Message(role: .user,
+                       content: "What happens in this clip?")],
+    videoURL: localFileURL)
+```
+
+Audio-only and other variants are exposed via the same
+`generate(_:)` overloads — see the Swift file
+[`CoreMLLLM.swift`](https://github.com/john-rocky/CoreML-LLM/blob/main/Sources/CoreMLLLM/CoreMLLLM.swift)
+for the full surface.
+<!-- swift-usage-end -->
+
+
+
+# Gemma 4 E2B — Core ML (ANE multimodal)
+
+Core ML port of [`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it) (the 2B-effective Gemma 4 / Gemma 3n decoder), optimized for Apple Neural Engine. Text + image + audio + short video, INT4 weights.
+
+> **Branches:** `main` is the long-running 4-chunk text+vision+audio bundle. The default ship target for [`CoreMLLLMChat`](https://github.com/john-rocky/CoreML-LLM) v1.6+ is the **`n1024`** branch (3-chunk merged decoder, slightly faster prefill). Both ship the same architecture — only the chunk topology and tokenizer artifacts differ. Pick whichever matches the Swift runtime you're using; if in doubt, use `n1024`.
+
+## Files (root, `n1024` branch — recommended)
+
+```
+chunk1.mlmodelc/                  # L0–7    — INT4 palettized
+chunk2_3way.mlmodelc/             # L8–24   — merged middle (3-chunk decoder)
+chunk3_3way.mlmodelc/             # L25–34 + lm_head — multifunction
+prefill_chunk{1..4}.mlmodelc/     # T=N prefill bodies (mlmodelc, weights shared
+                                  # with decode chunks via hardlink)
+vision.mlmodelc/                  # SigLIP encoder, 322 MB
+vision_video.mlmodelc/            # video frame encoder (64 tok/frame)
+audio.mlmodelc/                   # 282 MB Whisper-style audio encoder
+
+embed_tokens_q8.bin               402 MB  — INT8 token embeddings (262144 × 1536)
+embed_tokens_scales.bin           512 KB
+embed_tokens_per_layer_q8.bin     2.19 GB — INT8 PLE
+embed_tokens_per_layer_scales.bin 512 KB
+per_layer_projection.bin          26 MB
+per_layer_norm_weight.bin         1 KB
+cos_{full,sliding}.npy            8 MB / 4 MB — precomputed RoPE cos
+sin_{full,sliding}.npy            8 MB / 4 MB — precomputed RoPE sin
+mel_filterbank.bin                129 KB — for audio path
+embed_proj_weight.npy             4.5 MB — vision/audio → text embed projection
+output_proj_{weight,bias}.npy     3 MB / 3 KB — audio output projection
+
+model_config.json                 434 B  — runtime config (hidden=1536, layers=35, …)
+audio_config.json                 402 B  — audio path config
+hf_model/{tokenizer.json, tokenizer_config.json, config.json}
+```
+
+The `main` branch additionally carries the older 4-chunk topology (`chunk2.mlmodelc` + `chunk3.mlmodelc` + `chunk4.mlmodelc`) and several legacy variant directories (`sdpa/`, `sdpa-8k/`, `swa/`, `stateless/`, `stateless-ctx2048/`, `lite/`, `lite-chunks/`, `mf/`, `w8a8-8k/`, `model.mlmodelc`, `model.mlpackage`). These are research builds — only the `chunk*.mlmodelc` (or `chunk{1,2_3way,3_3way}.mlmodelc`) family is the shipping path.
+
+## Why so many sidecars
+
+Gemma 4 / 3n uses a per-layer embedding (PLE) bank that dwarfs the token embedding. Loading PLE through Core ML would dequant the whole 2.19 GB into the CPU heap. Instead, the raw INT8 + scale files are mmap'd in Swift and only the rows actually touched are dequantized on the fly. The chunks themselves stay ANE-resident.
+
+`cos`/`sin` `.npy` are pre-baked so the Swift side doesn't ship a RoPE builder.
+
+## Tokenizer
+
+Already in `hf_model/`. Or pull from upstream:
+
+```python
+from transformers import AutoTokenizer
+tok = AutoTokenizer.from_pretrained("google/gemma-4-E2B-it")
+```
+
+## Standalone usage (Python / Mac)
+
+```python
+from huggingface_hub import snapshot_download
+import coremltools as ct, json
+
+local = snapshot_download(
+    "mlboydaisuke/gemma-4-E2B-coreml", revision="n1024",
+    allow_patterns=[
+        "chunk1.mlmodelc/*", "chunk2_3way.mlmodelc/*", "chunk3_3way.mlmodelc/*",
+        "prefill_chunk*.mlmodelc/*",
+        "embed_tokens*.bin", "per_layer_*.bin",
+        "cos_*.npy", "sin_*.npy",
+        "model_config.json", "hf_model/*",
+    ],
+)
+cfg = json.load(open(f"{local}/model_config.json"))
+chunks = [
+    ct.models.MLModel(f"{local}/chunk1.mlmodelc"),
+    ct.models.MLModel(f"{local}/chunk2_3way.mlmodelc"),
+    ct.models.MLModel(f"{local}/chunk3_3way.mlmodelc"),
+]
+```
+
+For a working end-to-end loop (PLE dequant, vision/audio injection, KV alias plumbing), see [`Sources/CoreMLLLM/ChunkedEngine.swift`](https://github.com/john-rocky/CoreML-LLM/blob/main/Sources/CoreMLLLM/ChunkedEngine.swift) — the canonical reference.
+
+## Vision / Audio
+
+- `vision.mlmodelc` expects `pixel_values (1, 3, 256, 256)` fp16, outputs `(1, 256, 1536)` text-aligned tokens.
+- `audio.mlmodelc` expects mel-spectrogram features (use `mel_filterbank.bin` for the front-end), outputs an audio token stream injected into the same text decoder.
+- `vision_video.mlmodelc` packs 64 tokens per frame for short video.
+
+## iOS / Mac app
+
+Pick **Gemma 4 E2B** in [`CoreMLLLMChat`](https://github.com/john-rocky/CoreML-LLM/tree/main/Examples/CoreMLLLMChat) — it auto-downloads this repo (the picker fetches the `n1024` branch by default) and runs it via `ChunkedEngine`.
+
+## Architecture
+
+| | value |
+|---|---:|
+| `num_hidden_layers` | 35 |
+| `hidden_size` | 1536 |
+| `num_key_value_heads` | 1 |
+| `intermediate_size` | 6144 |
+| `num_kv_shared_layers` | 20 |
+| KV producers (sliding/full) | L13 / L14 |
+| sliding window | 512 |
+| context length (shipping) | 1024 (n1024) / 2048 (main) |
+| vocab | 262144 |
+
+## License
+
+Inherits the [Gemma terms of use](https://ai.google.dev/gemma/terms).

audio.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787af9d90589dada22454417de6cd75a7dd63d782ea231dc88acc1d37213184b
+size 243

audio.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f22e4537a4a60b0fa8843657072b2d5d9751b9027366167fc32ccf3137d916
+size 392

audio.mlmodelc/metadata.json

@@ -0,0 +1,84 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Mixed (Float16, Int32, Int8)",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 250 × 1536)",
+        "shortDescription" : "",
+        "shape" : "[1, 250, 1536]",
+        "name" : "audio_features",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 9,
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 1,
+      "Ios18.mul" : 313,
+      "Ios18.softmax" : 12,
+      "Ios18.matmul" : 36,
+      "Ios16.reduceMean" : 109,
+      "Ios18.sigmoid" : 12,
+      "Split" : 12,
+      "Select" : 12,
+      "Ios18.add" : 169,
+      "Ios18.layerNorm" : 2,
+      "Ios18.reshape" : 109,
+      "Pad" : 60,
+      "Ios18.linear" : 123,
+      "Ios18.conv" : 14,
+      "Ios18.relu" : 2,
+      "Ios18.clip" : 312,
+      "Ios18.silu" : 36,
+      "Stack" : 24,
+      "Ios18.pow" : 218,
+      "Ios18.transpose" : 75,
+      "Ios18.cast" : 144,
+      "Ios18.tanh" : 12,
+      "Ios18.sliceByIndex" : 528,
+      "Ios18.constexprBlockwiseShiftScale" : 148
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+
+    ],
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-04-11",
+      "com.github.apple.coremltools.source" : "torch==2.11.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1000 × 128)",
+        "shortDescription" : "",
+        "shape" : "[1, 1000, 128]",
+        "name" : "input_features",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "audio",
+    "method" : "predict"
+  }
+]

audio.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e067cc94f6f826d3d8f150cea14ba086b7a3555bffa72ffb76a0743ff98038
+size 295373248

audio_config.json

@@ -0,0 +1,19 @@
+{
+  "sampling_rate": 16000,
+  "feature_size": 128,
+  "frame_length": 320,
+  "hop_length": 160,
+  "fft_length": 512,
+  "mel_floor": 1e-05,
+  "min_frequency": 0,
+  "max_frequency": 8000,
+  "log_offset": 0.001,
+  "preemphasis": 0.97,
+  "mel_frames": 1000,
+  "num_tokens": 250,
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "eoa_token_id": 258883,
+  "ms_per_token": 40,
+  "quantization": "int8"
+}

chunk1.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd907c451c760d6a5bd6cbb2e2aea4d4385b452435f53b7bdec2dcb76a6f65fc
+size 243

chunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c581491e5aef9c16869f261f5ccc31a404a2152054b71459531d19908b0766da
+size 616

chunk1.mlmodelc/metadata.json

@@ -0,0 +1,162 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Mixed (Float16, Palettized (10 bits), Palettized (11 bits), Palettized (12 bits), Palettized (7 bits), Palettized (8 bits), UInt4)",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1536)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1536]",
+        "name" : "hidden_states_out",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 9,
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 48,
+      "Ios18.mul" : 335,
+      "Ios18.softmax" : 12,
+      "Ios18.matmul" : 24,
+      "Ios16.reduceMean" : 12,
+      "Split" : 108,
+      "Ios18.readState" : 24,
+      "Tile" : 48,
+      "Ios18.add" : 108,
+      "Ios18.writeState" : 24,
+      "Ios18.sliceUpdate" : 24,
+      "Ios18.layerNorm" : 84,
+      "Pad" : 20,
+      "Ios18.reshape" : 144,
+      "Ios18.constexprLutToDense" : 108,
+      "Ios18.conv" : 84,
+      "Ios18.concat" : 108,
+      "Ios18.transpose" : 180,
+      "Ios18.sub" : 1,
+      "Ios18.pow" : 24,
+      "Ios18.gelu" : 24,
+      "Ios18.linear" : 24,
+      "Ios18.sliceByIndex" : 56,
+      "Ios18.squeeze" : 36
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+      {
+        "dataType" : "Float16",
+        "isOptional" : "0",
+        "formattedType" : "State (Float16 24 × 1 × 512 × 512)",
+        "shortDescription" : "",
+        "shape" : "[24, 1, 512, 512]",
+        "name" : "kv_cache_0",
+        "type" : "State"
+      }
+    ],
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-04-09",
+      "com.github.apple.coremltools.source" : "torch==2.11.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1536)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1536]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 8960)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 8960]",
+        "name" : "per_layer_combined",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 256]",
+        "name" : "cos_s",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 256]",
+        "name" : "sin_s",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "cos_f",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "sin_f",
+        "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" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 1)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 1]",
+        "name" : "update_mask",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "chunk1",
+    "method" : "predict"
+  }
+]

chunk1.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef2217c8492f349cee65f12f53a6fcced7410d00844b119209c8567c03cadac
+size 224593536

chunk2.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515f00967033a2e15bc723d7713d5008382ae7600841855da258a2525c712818
+size 243

chunk2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a017df2d9900f0a32b1b949e3af4d144c056383f12772be20fd6c12986eb638
+size 720

chunk2.mlmodelc/metadata.json

@@ -0,0 +1,202 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Mixed (Float16, Palettized (10 bits), Palettized (11 bits), Palettized (12 bits), Palettized (13 bits), Palettized (7 bits), Palettized (8 bits), UInt4)",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1536)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1536]",
+        "name" : "hidden_states_out",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 256]",
+        "name" : "kv13_k",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 256]",
+        "name" : "kv13_v",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 512]",
+        "name" : "kv14_k",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 512]",
+        "name" : "kv14_v",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 9,
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 30,
+      "Ios18.mul" : 246,
+      "Ios18.softmax" : 12,
+      "Ios18.matmul" : 24,
+      "Ios16.reduceMean" : 3,
+      "Split" : 90,
+      "Ios18.readState" : 6,
+      "Tile" : 12,
+      "Ios18.add" : 72,
+      "Ios18.writeState" : 6,
+      "Ios18.sliceUpdate" : 6,
+      "Ios18.layerNorm" : 75,
+      "Pad" : 4,
+      "Ios18.reshape" : 72,
+      "Ios18.constexprLutToDense" : 90,
+      "Ios18.conv" : 66,
+      "Ios18.concat" : 90,
+      "Ios18.transpose" : 108,
+      "Ios18.sub" : 1,
+      "Ios18.pow" : 6,
+      "Ios18.gelu" : 24,
+      "Ios18.linear" : 24,
+      "Ios18.sliceByIndex" : 22,
+      "Ios18.squeeze" : 18
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+      {
+        "dataType" : "Float16",
+        "isOptional" : "0",
+        "formattedType" : "State (Float16 24 × 1 × 512 × 512)",
+        "shortDescription" : "",
+        "shape" : "[24, 1, 512, 512]",
+        "name" : "kv_cache_0",
+        "type" : "State"
+      }
+    ],
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-04-09",
+      "com.github.apple.coremltools.source" : "torch==2.11.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1536)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1536]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 8960)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 8960]",
+        "name" : "per_layer_combined",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 256]",
+        "name" : "cos_s",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 256]",
+        "name" : "sin_s",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "cos_f",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "sin_f",
+        "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" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 1)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 1]",
+        "name" : "update_mask",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "chunk2",
+    "method" : "predict"
+  }
+]

chunk2.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30f8e0ff131ba884c980f3731b67a55b021f3f1b58194cb8a36320cf8bbf81b
+size 348158016

chunk3.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433b8d279ee1280cff500e24de8f31c7f10881a49cd34c3f64137511704613ae
+size 243

chunk3.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8de33ff562cb4083c21f249f283ba21da97e8ce9f970a6dee338680915c46d8
+size 672

chunk3.mlmodelc/metadata.json

@@ -0,0 +1,190 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Mixed (Float16, Palettized (10 bits), Palettized (11 bits), Palettized (13 bits), Palettized (17 bits), Palettized (7 bits), UInt4)",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "token_id",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "token_logit",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 9,
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 23,
+      "Ios18.softmax" : 11,
+      "Ios18.mul" : 202,
+      "Ios18.matmul" : 22,
+      "Split" : 78,
+      "Ios18.gatherAlongAxis" : 1,
+      "Tile" : 4,
+      "Ios18.add" : 55,
+      "Ios18.reduceArgmax" : 1,
+      "Ios18.layerNorm" : 67,
+      "Ios18.reshape" : 52,
+      "Ios18.constexprLutToDense" : 78,
+      "Ios18.linear" : 22,
+      "Ios18.conv" : 56,
+      "Ios18.gelu" : 22,
+      "Ios18.concat" : 78,
+      "Ios18.tanh" : 1,
+      "Ios18.transpose" : 91,
+      "Ios18.sliceByIndex" : 11,
+      "Ios18.squeeze" : 13
+    },
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+
+    ],
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-04-09",
+      "com.github.apple.coremltools.source" : "torch==2.11.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1536)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1536]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 8960)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 8960]",
+        "name" : "per_layer_combined",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 256]",
+        "name" : "cos_s",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 256]",
+        "name" : "sin_s",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "cos_f",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 512]",
+        "name" : "sin_f",
+        "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" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 256]",
+        "name" : "kv13_k",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 256)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 256]",
+        "name" : "kv13_v",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 512]",
+        "name" : "kv14_k",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 512 × 512)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 512, 512]",
+        "name" : "kv14_v",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "chunk3",
+    "method" : "predict"
+  }
+]

chunk3.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba86daad260a6c05877145540541fd7a87823fb618d15e8cc6ec0d9ab4e570e
+size 561924928

cos_full.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fa3ab781c1ec56286864598a66e5f8ddaffdd4d570948fb03cc8984c70ecca
+size 1048704

cos_sliding.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490c6b33d055d55c7ea1153f69945da4c83c1a3bd0da158d7ed3d02bde189a0d
+size 524416

embed_proj_weight.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4e61ba9b02186427d6e20bb20bc40661e6fd21b6bb0527829fb954405e7dbf
+size 4718720

embed_tokens_per_layer_q8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1af367cde6fcb67a48925c0c566b0aac11946248d8e3cfebc4027550947cd8
+size 2348810240

embed_tokens_per_layer_scales.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a439606004e3372158eed3efd4c671cefea056122afb93c546108411ea41b057
+size 524288

embed_tokens_q8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2286db227b17e71fb3908983999876625c811295055457b6f798e0f09969797a
+size 402653184

embed_tokens_scales.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db47a8808d782d3c2b1ab722833b425e0bb4755360409d766acb89a4a8443461
+size 524288

hf_model/config.json

@@ -0,0 +1,190 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1536,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 35,
+    "num_key_value_heads": 1,
+    "num_kv_shared_layers": 20,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": true,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0.dev0",
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

hf_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

hf_model/tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "type": "object",
+    "properties": {
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "content": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
+        "type": "array",
+        "items": {
+          "type": "object",
+          "properties": {
+            "type": {
+              "const": "function"
+            },
+            "function": {
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
+              "properties": {
+                "name": {
+                  "type": "string"
+                },
+                "arguments": {
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call",
+                  "additionalProperties": {}
+                }
+              }
+            }
+          }
+        }
+      }
+    },
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

lite-chunks/chunk1.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f43848234c83768f456ced9021d89bf8a176269e93e6d24917b2cea30b0344e
+size 243

lite-chunks/chunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f153053e142c607b1998c1871ea3cb2dfbb166783093145bee663c4ca84ad28f
+size 678

lite-chunks/chunk1.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edcdea405378e1c413487cc23eae7f0d88644ce003b634bcdd3a0bedf9546a86
+size 484892288

lite-chunks/chunk2.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105d47ff96b357c5a4e44f3fa75fdd2119ae3dcf916beb0c3c26be58d2ff32a6
+size 243

lite-chunks/chunk2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6c80ff346337915cd3b66231c73db9381c06db2665dd370ef59767c0d9afbb
+size 633

lite-chunks/chunk2.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade112884788cfa7723fa54f03a4e2f751197ba40441343c63beba5ec08aa3aa
+size 852950784

lite-chunks/model_config.json

@@ -0,0 +1,18 @@
+{
+  "model_name": "gemma4-e2b-lite-chunks",
+  "architecture": "gemma4",
+  "hidden_size": 1536,
+  "num_hidden_layers": 35,
+  "context_length": 512,
+  "vocab_size": 262144,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "per_layer_dim": 256,
+  "embed_scale": 39.191835884530846,
+  "per_layer_model_projection_scale": 0.02551551815399144,
+  "per_layer_input_scale": 0.7071067811865476,
+  "per_layer_embed_scale": 16.0,
+  "external_embeddings": true,
+  "has_multimodal": true,
+  "chunked": true
+}

lite/model.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d76da9c8e80ee8fa80650037f75b23ef97873de075fc4aeeca8355d1f24fe77
+size 243

lite/model.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926c0207bac21850898edb761b030cfa21743319dbae7b4d4d04e5f0c6b3aebb
+size 588

lite/model.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a90518966541e73dc4e2477973391dbebc7efa3f8b6f931e4d74362dbedeab1
+size 1337046592

lite/model_config.json

@@ -0,0 +1,17 @@
+{
+  "model_name": "gemma4-e2b-lite",
+  "architecture": "gemma4",
+  "hidden_size": 1536,
+  "num_hidden_layers": 35,
+  "context_length": 512,
+  "vocab_size": 262144,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "per_layer_dim": 256,
+  "embed_scale": 39.191835884530846,
+  "per_layer_model_projection_scale": 0.02551551815399144,
+  "per_layer_input_scale": 0.7071067811865476,
+  "per_layer_embed_scale": 16.0,
+  "external_embeddings": true,
+  "has_multimodal": true
+}

mel_filterbank.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427860b9a9429175f0e450512def4224f46ced89960dfb1d9cf7479d7e485e2b
+size 131584

mf/chunk1.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db31b52905612845c8825d4e104673bded13be17a6473905b939241f880646b
+size 243

mf/chunk1.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b145aa3b71ec1af8e83efd69905de1cb606e9d75a51cf0e6ae5481bb0e516bf
+size 1360