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

FunctionGemmaANEUnifiedStateful.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a51ac9b315028b67037095c93eff2daacf6abdecb1a355167241660acf9001
+size 243

FunctionGemmaANEUnifiedStateful.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b9f702fcb84621d301af02048a1c45508c26843094f3996265eb1f6e651f15
+size 1853

FunctionGemmaANEUnifiedStateful.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f194bf64df8455907febce356113d0e711b989ae03e945db11c386c905ea6eb
+size 536735872

README.md

@@ -0,0 +1,118 @@
+---
+license: gemma
+language:
+- en
+tags:
+- function-calling
+- tool-calling
+- gemma3
+- coreml
+- ane
+- on-device
+base_model: google/functiongemma-270m-it
+library_name: coreml
+pipeline_tag: text-generation
+---
+
+# FunctionGemma 270M — CoreML (fp16)
+
+A Core ML export of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it),
+optimized for the Apple Neural Engine on iOS 18 / macOS 15. The 18-layer
+transformer is reshaped into Apple's **BC1S layout** (`(B, C, 1, T)`
+channel-last with 1×1 `Conv2d` projections and per-head split attention)
+and the K/V cache lives in **`MLState`** slots, so token-by-token decode
+sends no tensor I/O back to the host.
+
+This is the **fp16 reference** build — full Float16 weights, no
+quantization. For the same accuracy with ~½ the disk and faster decode,
+see the
+[Palettize-8 variant](https://huggingface.co/aufklarer/FunctionGemma-270M-CoreML-Palettize8).
+
+## Model
+
+| | |
+|---|---|
+| Parameters | 270M |
+| Architecture | Gemma 3 (18 layers, 4 query heads, 1 KV head, head_dim 256, hidden 640, MLP 2048) |
+| Quantization | none (Float16 weights, fp16 compute) |
+| Format | Core ML `.mlmodelc` (ML Program) |
+| Cache layout | BC1S `MLState`, fixed cache length 128 |
+| Shapes | T_q ∈ {1, 128} via `EnumeratedShapes` |
+| File size | 513 MB model + 33 MB tokenizer ≈ 546 MB total |
+| Min target | **iOS 18 / macOS 15** |
+| Compute units | `cpuAndNeuralEngine` (required — CPU-only emulation diverges) |
+
+## Files
+
+| File | Size | Description |
+|---|---|---|
+| `FunctionGemmaANEUnifiedStateful.mlmodelc/` | 513 MB | Compiled Core ML model. Load with `MLModel(contentsOf:)`. |
+| `config.json` | ~2 KB | Architecture metadata (state names, input/output names, deployment target). |
+| `chat_template.jinja` | ~1 KB | Jinja chat template used by `tokenizer.apply_chat_template`. |
+| `tokenizer.json` | ~33 MB | Hugging Face `tokenizers` fast SentencePiece model. |
+| `tokenizer_config.json` | ~1 KB | Tokenizer settings. |
+
+## Performance
+
+Measured on Apple M-series Mac via `cpuAndNeuralEngine`, on the canonical
+"Convert 23 USD to EUR" tool-call prompt (91-token prompt → 31-token
+function call), warmed.
+
+| | Value |
+|---|---|
+| Prefill (128 tokens) | 8.5 ms |
+| Decode | 5.65 ms/token (**177 tok/s**) |
+| End-to-end (32 tokens) | ~185 ms |
+| Swift peak RSS (warm) | **~37 MB** private + ~510 MB mmap'd from disk (evictable) |
+| Compute-plan device | 96 %+ of ops prefer `neuralEngine` |
+| Output | Byte-identical to PyTorch fp32 reference on the canonical prompt |
+
+## Usage
+
+### Swift (iOS 18 / macOS 15)
+
+```swift
+import CoreML
+
+let url = URL(fileURLWithPath: "FunctionGemmaANEUnifiedStateful.mlmodelc")
+let config = MLModelConfiguration()
+config.computeUnits = .cpuAndNeuralEngine
+let model = try MLModel(contentsOf: url, configuration: config)
+let state = model.makeState()
+
+// Build prefill inputs (input_ids, cos/sin tables, attention mask,
+// write_mask=ones, logits_mask one-hot at the last prompt position),
+// then for decode call repeatedly with T_q=1 inputs and a one-hot
+// write_mask at the current cache slot.
+let output = try await model.prediction(from: prefillInputs, using: state)
+let logits = output.featureValue(for: "logits")!.multiArrayValue!
+```
+
+The full prefill + decode driver is published as part of the
+[speech-swift](https://github.com/soniqo/speech-swift) SDK.
+
+### Python (coremltools, macOS only)
+
+```python
+import coremltools as ct
+import numpy as np
+
+model = ct.models.MLModel(
+    "FunctionGemmaANEUnifiedStateful.mlpackage",
+    compute_units=ct.ComputeUnit.CPU_AND_NE,
+)
+state = model.make_state()
+out = model.predict(prefill_inputs, state=state)
+next_id = int(out["logits"][0].argmax())
+```
+
+## Source
+
+Upstream model: **[google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it)**
+— Gemma 3 270M instruction-tuned for structured function calls.
+
+## Links
+
+- [speech-swift](https://github.com/soniqo/speech-swift) — Apple SDK
+- [soniqo.audio](https://soniqo.audio) — website
+- [blog](https://soniqo.audio/blog)

chat_template.jinja

@@ -0,0 +1,279 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{- key }}:{description:<escape>{{ value['description'] }}<escape>
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    ,enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <escape>{{- item -}}<escape>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <escape>{{- req_item -}}<escape>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            ,type:<escape>{{ value['type'] | upper }}<escape>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{% macro format_function_declaration(tool_data) -%}
+declaration:{{- tool_data['function']['name'] -}}
+{description:<escape>{{- tool_data['function']['description'] -}}<escape>
+{%- set params = tool_data['function']['parameters'] -%}
+{%- if params -%}
+    ,parameters:{
+    {%- if params['properties'] -%}
+        properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+    {%- endif -%}
+    {%- if params['required'] -%}
+        required:[
+        {%- for item in params['required'] -%}
+            <escape>{{- item -}}<escape>
+            {{- ',' if not loop.last -}}
+        {%- endfor -%}
+        ],
+    {%- endif -%}
+    {%- if params['type'] -%}
+        type:<escape>{{- params['type'] | upper -}}<escape>}
+    {%- endif -%}
+{%- endif -%}
+}
+{%- endmacro -%}
+{% macro format_argument(argument, escape_keys=True) -%}
+{%- if argument is string -%}
+    {{- '<escape>' + argument + '<escape>' -}}
+{%- elif argument is boolean -%}
+    {%- if argument -%}
+        {{- 'true' -}}
+    {%- else -%}
+        {{- 'false' -}}
+    {%- endif -%}
+{%- elif argument is mapping -%}
+    {{- '{' -}}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in argument | dictsort -%}
+        {%- if ns.found_first %},{% endif -%}
+        {%- set ns.found_first = true -%}
+        {%- if escape_keys -%}
+            {{- '<escape>' + key + '<escape>' -}}
+        {%- else -%}
+            {{- key -}}
+        {%- endif -%}
+        :{{- format_argument(value, escape_keys=escape_keys) -}}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- elif argument is sequence -%}
+    {{- '[' -}}
+    {%- for item in argument -%}
+        {{- format_argument(item, escape_keys=escape_keys) -}}
+        {%- if not loop.last %},{% endif -%}
+    {%- endfor -%}
+    {{- ']' -}}
+{%- else -%}
+    {{- argument -}}
+{%- endif -%}
+{%- endmacro -%}
+{{ bos_token }}
+{%- set ns = namespace(prev_message_type=None) -%}
+{#- Tool Declarations -#}
+{%- set loop_messages = messages -%}
+{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+    {{- '<start_of_turn>developer\n' -}}
+    {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {%- if item['type'] == 'text' -%}
+                    {{- item['text'] | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<start_function_declaration>' -}}
+            {{- format_function_declaration(tool) | trim }}
+            {{- '<end_function_declaration>' -}}
+        {%- endfor %}
+    {%- endif -%}
+    {{- '<end_of_turn>\n' }}
+{%- endif %}
+{#- Loop through messages. -#}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {#- Rename "assistant" to "model". -#}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {%- if role != 'tool' -%}
+        {%- if ns.prev_message_type != 'tool_response' -%}
+            {{- '<start_of_turn>' + role + '\n' }}
+        {%- endif -%}
+        {%- set ns.prev_message_type = None -%}
+        {%- if 'content' in message and message['content'] is not none -%}
+            {%- if message['content'] is string -%}
+                {{ message['content'] | trim }}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'image' -%}
+                        {{ '<start_of_image>' }}
+                    {%- elif item['type'] == 'text' -%}
+                        {{ item['text'] | trim }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in user/assistant message") }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'content' -%}
+        {%- endif -%}
+        {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
+            {#- Tool Calls -#}
+            {%- for tool_call in message['tool_calls'] -%}
+                {% set function = tool_call['function'] %}
+                {{-  '<start_function_call>call:' + function['name'] + '{' -}}
+                {%- if 'arguments' in function -%}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns.found_first %},{% endif -%}
+                            {%- set ns.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {# This handles string-JSON, just in case #}
+                    {{ function['arguments'] }}
+                    {%- endif %}
+                {%- endif -%}
+                {{- '}<end_function_call>' -}}
+            {%- endfor -%}
+            {%- if loop.last -%}
+                {{ '<start_function_response>' }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'tool_call' -%}
+        {%- endif -%}
+    {%- else -%}
+        {#- Tool Responses -#}
+        {%- if 'content' in message and message['content'] -%}
+            {%- if message['content'] is mapping -%}
+                {%- if 'name' in message['content'] and 'response' in message['content'] -%}
+                    {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content']['response'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- elif 'name' in message -%}
+                    {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- else -%}
+                    {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                {%- endif -%}
+            {%- elif message['content'] is string -%}
+                {%- if 'name' in message -%}
+                     {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
+                {%- else -%}
+                     {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item is mapping -%}
+                        {%- if 'name' in item and 'response' in item -%}
+                            {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item['response'] | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- elif 'name' in message -%}
+                            {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- else -%}
+                            {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                        {%- endif -%}
+                    {%- else -%}
+                        {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set ns.prev_message_type = 'tool_response' -%}
+    {%- endif -%}
+    {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
+        {{ '<end_of_turn>\n' }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<start_of_turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,75 @@
+{
+  "modelName": "functiongemma-270m-it",
+  "modelFamily": "functiongemma",
+  "format": "coreml-mlprogram",
+  "architecture": "ane_unified_state",
+  "source": "huggingface",
+  "hfRepo": "google/functiongemma-270m-it",
+  "tSpecs": [
+    1,
+    128
+  ],
+  "cacheSeqLen": 128,
+  "numLayers": 18,
+  "numKvHeads": 1,
+  "headDim": 256,
+  "hiddenSize": 640,
+  "computePrecision": "float16",
+  "quantization": "none",
+  "computeUnits": "cpu_and_ne",
+  "stateNames": [
+    "k_cache_0",
+    "v_cache_0",
+    "k_cache_1",
+    "v_cache_1",
+    "k_cache_2",
+    "v_cache_2",
+    "k_cache_3",
+    "v_cache_3",
+    "k_cache_4",
+    "v_cache_4",
+    "k_cache_5",
+    "v_cache_5",
+    "k_cache_6",
+    "v_cache_6",
+    "k_cache_7",
+    "v_cache_7",
+    "k_cache_8",
+    "v_cache_8",
+    "k_cache_9",
+    "v_cache_9",
+    "k_cache_10",
+    "v_cache_10",
+    "k_cache_11",
+    "v_cache_11",
+    "k_cache_12",
+    "v_cache_12",
+    "k_cache_13",
+    "v_cache_13",
+    "k_cache_14",
+    "v_cache_14",
+    "k_cache_15",
+    "v_cache_15",
+    "k_cache_16",
+    "v_cache_16",
+    "k_cache_17",
+    "v_cache_17"
+  ],
+  "requires": {
+    "minimumDeploymentTarget": "iOS 18 / macOS 15",
+    "feature": "ANE BC1S unified + MLState"
+  },
+  "inputs": [
+    "input_ids",
+    "cos_full",
+    "sin_full",
+    "cos_sliding",
+    "sin_sliding",
+    "write_mask",
+    "attention_mask",
+    "logits_mask"
+  ],
+  "outputs": [
+    "logits"
+  ]
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
+size 33384898

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>",
+    "sfr_token": "<start_function_response>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sfr_token": "<start_function_response>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}