aufklarer commited on
Commit
ec7194d
·
verified ·
1 Parent(s): 5fe2f61

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
FunctionGemmaANEUnifiedStateful.mlmodelc/analytics/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a51ac9b315028b67037095c93eff2daacf6abdecb1a355167241660acf9001
3
+ size 243
FunctionGemmaANEUnifiedStateful.mlmodelc/coremldata.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b9f702fcb84621d301af02048a1c45508c26843094f3996265eb1f6e651f15
3
+ size 1853
FunctionGemmaANEUnifiedStateful.mlmodelc/model.mil ADDED
The diff for this file is too large to render. See raw diff
 
FunctionGemmaANEUnifiedStateful.mlmodelc/weights/weight.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f194bf64df8455907febce356113d0e711b989ae03e945db11c386c905ea6eb
3
+ size 536735872
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: gemma
3
+ language:
4
+ - en
5
+ tags:
6
+ - function-calling
7
+ - tool-calling
8
+ - gemma3
9
+ - coreml
10
+ - ane
11
+ - on-device
12
+ base_model: google/functiongemma-270m-it
13
+ library_name: coreml
14
+ pipeline_tag: text-generation
15
+ ---
16
+
17
+ # FunctionGemma 270M — CoreML (fp16)
18
+
19
+ A Core ML export of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it),
20
+ optimized for the Apple Neural Engine on iOS 18 / macOS 15. The 18-layer
21
+ transformer is reshaped into Apple's **BC1S layout** (`(B, C, 1, T)`
22
+ channel-last with 1×1 `Conv2d` projections and per-head split attention)
23
+ and the K/V cache lives in **`MLState`** slots, so token-by-token decode
24
+ sends no tensor I/O back to the host.
25
+
26
+ This is the **fp16 reference** build — full Float16 weights, no
27
+ quantization. For the same accuracy with ~½ the disk and faster decode,
28
+ see the
29
+ [Palettize-8 variant](https://huggingface.co/aufklarer/FunctionGemma-270M-CoreML-Palettize8).
30
+
31
+ ## Model
32
+
33
+ | | |
34
+ |---|---|
35
+ | Parameters | 270M |
36
+ | Architecture | Gemma 3 (18 layers, 4 query heads, 1 KV head, head_dim 256, hidden 640, MLP 2048) |
37
+ | Quantization | none (Float16 weights, fp16 compute) |
38
+ | Format | Core ML `.mlmodelc` (ML Program) |
39
+ | Cache layout | BC1S `MLState`, fixed cache length 128 |
40
+ | Shapes | T_q ∈ {1, 128} via `EnumeratedShapes` |
41
+ | File size | 513 MB model + 33 MB tokenizer ≈ 546 MB total |
42
+ | Min target | **iOS 18 / macOS 15** |
43
+ | Compute units | `cpuAndNeuralEngine` (required — CPU-only emulation diverges) |
44
+
45
+ ## Files
46
+
47
+ | File | Size | Description |
48
+ |---|---|---|
49
+ | `FunctionGemmaANEUnifiedStateful.mlmodelc/` | 513 MB | Compiled Core ML model. Load with `MLModel(contentsOf:)`. |
50
+ | `config.json` | ~2 KB | Architecture metadata (state names, input/output names, deployment target). |
51
+ | `chat_template.jinja` | ~1 KB | Jinja chat template used by `tokenizer.apply_chat_template`. |
52
+ | `tokenizer.json` | ~33 MB | Hugging Face `tokenizers` fast SentencePiece model. |
53
+ | `tokenizer_config.json` | ~1 KB | Tokenizer settings. |
54
+
55
+ ## Performance
56
+
57
+ Measured on Apple M-series Mac via `cpuAndNeuralEngine`, on the canonical
58
+ "Convert 23 USD to EUR" tool-call prompt (91-token prompt → 31-token
59
+ function call), warmed.
60
+
61
+ | | Value |
62
+ |---|---|
63
+ | Prefill (128 tokens) | 8.5 ms |
64
+ | Decode | 5.65 ms/token (**177 tok/s**) |
65
+ | End-to-end (32 tokens) | ~185 ms |
66
+ | Swift peak RSS (warm) | **~37 MB** private + ~510 MB mmap'd from disk (evictable) |
67
+ | Compute-plan device | 96 %+ of ops prefer `neuralEngine` |
68
+ | Output | Byte-identical to PyTorch fp32 reference on the canonical prompt |
69
+
70
+ ## Usage
71
+
72
+ ### Swift (iOS 18 / macOS 15)
73
+
74
+ ```swift
75
+ import CoreML
76
+
77
+ let url = URL(fileURLWithPath: "FunctionGemmaANEUnifiedStateful.mlmodelc")
78
+ let config = MLModelConfiguration()
79
+ config.computeUnits = .cpuAndNeuralEngine
80
+ let model = try MLModel(contentsOf: url, configuration: config)
81
+ let state = model.makeState()
82
+
83
+ // Build prefill inputs (input_ids, cos/sin tables, attention mask,
84
+ // write_mask=ones, logits_mask one-hot at the last prompt position),
85
+ // then for decode call repeatedly with T_q=1 inputs and a one-hot
86
+ // write_mask at the current cache slot.
87
+ let output = try await model.prediction(from: prefillInputs, using: state)
88
+ let logits = output.featureValue(for: "logits")!.multiArrayValue!
89
+ ```
90
+
91
+ The full prefill + decode driver is published as part of the
92
+ [speech-swift](https://github.com/soniqo/speech-swift) SDK.
93
+
94
+ ### Python (coremltools, macOS only)
95
+
96
+ ```python
97
+ import coremltools as ct
98
+ import numpy as np
99
+
100
+ model = ct.models.MLModel(
101
+ "FunctionGemmaANEUnifiedStateful.mlpackage",
102
+ compute_units=ct.ComputeUnit.CPU_AND_NE,
103
+ )
104
+ state = model.make_state()
105
+ out = model.predict(prefill_inputs, state=state)
106
+ next_id = int(out["logits"][0].argmax())
107
+ ```
108
+
109
+ ## Source
110
+
111
+ Upstream model: **[google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it)**
112
+ — Gemma 3 270M instruction-tuned for structured function calls.
113
+
114
+ ## Links
115
+
116
+ - [speech-swift](https://github.com/soniqo/speech-swift) — Apple SDK
117
+ - [soniqo.audio](https://soniqo.audio) — website
118
+ - [blog](https://soniqo.audio/blog)
chat_template.jinja ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- macro format_parameters(properties, required) -%}
2
+ {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
3
+ {%- set ns = namespace(found_first=false) -%}
4
+ {%- for key, value in properties | dictsort -%}
5
+ {%- if key not in standard_keys -%}
6
+ {%- if ns.found_first %},{% endif -%}
7
+ {%- set ns.found_first = true -%}
8
+ {{- key }}:{description:<escape>{{ value['description'] }}<escape>
9
+ {%- if value['type'] | upper == 'STRING' -%}
10
+ {%- if value['enum'] -%}
11
+ ,enum:{{ format_argument(value['enum']) }}
12
+ {%- endif -%}
13
+ {%- elif value['type'] | upper == 'OBJECT' -%}
14
+ ,properties:{
15
+ {%- if value['properties'] is defined and value['properties'] is mapping -%}
16
+ {{- format_parameters(value['properties'], value['required'] | default([])) -}}
17
+ {%- elif value is mapping -%}
18
+ {{- format_parameters(value, value['required'] | default([])) -}}
19
+ {%- endif -%}
20
+ }
21
+ {%- if value['required'] -%}
22
+ ,required:[
23
+ {%- for item in value['required'] | default([]) -%}
24
+ <escape>{{- item -}}<escape>
25
+ {%- if not loop.last %},{% endif -%}
26
+ {%- endfor -%}
27
+ ]
28
+ {%- endif -%}
29
+ {%- elif value['type'] | upper == 'ARRAY' -%}
30
+ {%- if value['items'] is mapping and value['items'] -%}
31
+ ,items:{
32
+ {%- set ns_items = namespace(found_first=false) -%}
33
+ {%- for item_key, item_value in value['items'] | dictsort -%}
34
+ {%- if item_value is not none -%}
35
+ {%- if ns_items.found_first %},{% endif -%}
36
+ {%- set ns_items.found_first = true -%}
37
+ {%- if item_key == 'properties' -%}
38
+ properties:{
39
+ {%- if item_value is mapping -%}
40
+ {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
41
+ {%- endif -%}
42
+ }
43
+ {%- elif item_key == 'required' -%}
44
+ required:[
45
+ {%- for req_item in item_value -%}
46
+ <escape>{{- req_item -}}<escape>
47
+ {%- if not loop.last %},{% endif -%}
48
+ {%- endfor -%}
49
+ ]
50
+ {%- elif item_key == 'type' -%}
51
+ {%- if item_value is string -%}
52
+ type:{{ format_argument(item_value | upper) }}
53
+ {%- else -%}
54
+ type:{{ format_argument(item_value | map('upper') | list) }}
55
+ {%- endif -%}
56
+ {%- else -%}
57
+ {{ item_key }}:{{ format_argument(item_value) }}
58
+ {%- endif -%}
59
+ {%- endif -%}
60
+ {%- endfor -%}
61
+ }
62
+ {%- endif -%}
63
+ {%- endif -%}
64
+ ,type:<escape>{{ value['type'] | upper }}<escape>}
65
+ {%- endif -%}
66
+ {%- endfor -%}
67
+ {%- endmacro -%}
68
+ {% macro format_function_declaration(tool_data) -%}
69
+ declaration:{{- tool_data['function']['name'] -}}
70
+ {description:<escape>{{- tool_data['function']['description'] -}}<escape>
71
+ {%- set params = tool_data['function']['parameters'] -%}
72
+ {%- if params -%}
73
+ ,parameters:{
74
+ {%- if params['properties'] -%}
75
+ properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
76
+ {%- endif -%}
77
+ {%- if params['required'] -%}
78
+ required:[
79
+ {%- for item in params['required'] -%}
80
+ <escape>{{- item -}}<escape>
81
+ {{- ',' if not loop.last -}}
82
+ {%- endfor -%}
83
+ ],
84
+ {%- endif -%}
85
+ {%- if params['type'] -%}
86
+ type:<escape>{{- params['type'] | upper -}}<escape>}
87
+ {%- endif -%}
88
+ {%- endif -%}
89
+ }
90
+ {%- endmacro -%}
91
+ {% macro format_argument(argument, escape_keys=True) -%}
92
+ {%- if argument is string -%}
93
+ {{- '<escape>' + argument + '<escape>' -}}
94
+ {%- elif argument is boolean -%}
95
+ {%- if argument -%}
96
+ {{- 'true' -}}
97
+ {%- else -%}
98
+ {{- 'false' -}}
99
+ {%- endif -%}
100
+ {%- elif argument is mapping -%}
101
+ {{- '{' -}}
102
+ {%- set ns = namespace(found_first=false) -%}
103
+ {%- for key, value in argument | dictsort -%}
104
+ {%- if ns.found_first %},{% endif -%}
105
+ {%- set ns.found_first = true -%}
106
+ {%- if escape_keys -%}
107
+ {{- '<escape>' + key + '<escape>' -}}
108
+ {%- else -%}
109
+ {{- key -}}
110
+ {%- endif -%}
111
+ :{{- format_argument(value, escape_keys=escape_keys) -}}
112
+ {%- endfor -%}
113
+ {{- '}' -}}
114
+ {%- elif argument is sequence -%}
115
+ {{- '[' -}}
116
+ {%- for item in argument -%}
117
+ {{- format_argument(item, escape_keys=escape_keys) -}}
118
+ {%- if not loop.last %},{% endif -%}
119
+ {%- endfor -%}
120
+ {{- ']' -}}
121
+ {%- else -%}
122
+ {{- argument -}}
123
+ {%- endif -%}
124
+ {%- endmacro -%}
125
+ {{ bos_token }}
126
+ {%- set ns = namespace(prev_message_type=None) -%}
127
+ {#- Tool Declarations -#}
128
+ {%- set loop_messages = messages -%}
129
+ {%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
130
+ {{- '<start_of_turn>developer\n' -}}
131
+ {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
132
+ {%- if messages[0]['content'] is string -%}
133
+ {{- messages[0]['content'] | trim -}}
134
+ {%- elif messages[0]['content'] is sequence -%}
135
+ {%- for item in messages[0]['content'] -%}
136
+ {%- if item['type'] == 'text' -%}
137
+ {{- item['text'] | trim -}}
138
+ {%- endif -%}
139
+ {%- endfor -%}
140
+ {%- endif -%}
141
+ {%- set loop_messages = messages[1:] -%}
142
+ {%- endif -%}
143
+ {%- if tools -%}
144
+ {%- for tool in tools %}
145
+ {{- '<start_function_declaration>' -}}
146
+ {{- format_function_declaration(tool) | trim }}
147
+ {{- '<end_function_declaration>' -}}
148
+ {%- endfor %}
149
+ {%- endif -%}
150
+ {{- '<end_of_turn>\n' }}
151
+ {%- endif %}
152
+ {#- Loop through messages. -#}
153
+ {%- for message in loop_messages -%}
154
+ {%- if (message['role'] == 'assistant') -%}
155
+ {#- Rename "assistant" to "model". -#}
156
+ {%- set role = "model" -%}
157
+ {%- else -%}
158
+ {%- set role = message['role'] -%}
159
+ {%- endif -%}
160
+ {%- if role != 'tool' -%}
161
+ {%- if ns.prev_message_type != 'tool_response' -%}
162
+ {{- '<start_of_turn>' + role + '\n' }}
163
+ {%- endif -%}
164
+ {%- set ns.prev_message_type = None -%}
165
+ {%- if 'content' in message and message['content'] is not none -%}
166
+ {%- if message['content'] is string -%}
167
+ {{ message['content'] | trim }}
168
+ {%- elif message['content'] is sequence -%}
169
+ {%- for item in message['content'] -%}
170
+ {%- if item['type'] == 'image' -%}
171
+ {{ '<start_of_image>' }}
172
+ {%- elif item['type'] == 'text' -%}
173
+ {{ item['text'] | trim }}
174
+ {%- endif -%}
175
+ {%- endfor -%}
176
+ {%- else -%}
177
+ {{ raise_exception("Invalid content type in user/assistant message") }}
178
+ {%- endif -%}
179
+ {%- set ns.prev_message_type = 'content' -%}
180
+ {%- endif -%}
181
+ {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
182
+ {#- Tool Calls -#}
183
+ {%- for tool_call in message['tool_calls'] -%}
184
+ {% set function = tool_call['function'] %}
185
+ {{- '<start_function_call>call:' + function['name'] + '{' -}}
186
+ {%- if 'arguments' in function -%}
187
+ {%- if function['arguments'] is mapping -%}
188
+ {%- set ns = namespace(found_first=false) -%}
189
+ {%- for key, value in function['arguments'] | dictsort -%}
190
+ {%- if ns.found_first %},{% endif -%}
191
+ {%- set ns.found_first = true -%}
192
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
193
+ {%- endfor -%}
194
+ {%- elif function['arguments'] is string -%}
195
+ {# This handles string-JSON, just in case #}
196
+ {{ function['arguments'] }}
197
+ {%- endif %}
198
+ {%- endif -%}
199
+ {{- '}<end_function_call>' -}}
200
+ {%- endfor -%}
201
+ {%- if loop.last -%}
202
+ {{ '<start_function_response>' }}
203
+ {%- endif -%}
204
+ {%- set ns.prev_message_type = 'tool_call' -%}
205
+ {%- endif -%}
206
+ {%- else -%}
207
+ {#- Tool Responses -#}
208
+ {%- if 'content' in message and message['content'] -%}
209
+ {%- if message['content'] is mapping -%}
210
+ {%- if 'name' in message['content'] and 'response' in message['content'] -%}
211
+ {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
212
+ {%- set response_ns = namespace(found_first=false) -%}
213
+ {%- for key, value in message['content']['response'] | dictsort -%}
214
+ {%- if response_ns.found_first %},{% endif -%}
215
+ {%- set response_ns.found_first = true -%}
216
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
217
+ {%- endfor -%}
218
+ {{- '}<end_function_response>' -}}
219
+ {%- elif 'name' in message -%}
220
+ {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
221
+ {%- set response_ns = namespace(found_first=false) -%}
222
+ {%- for key, value in message['content'] | dictsort -%}
223
+ {%- if response_ns.found_first %},{% endif -%}
224
+ {%- set response_ns.found_first = true -%}
225
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
226
+ {%- endfor -%}
227
+ {{- '}<end_function_response>' -}}
228
+ {%- else -%}
229
+ {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
230
+ {%- endif -%}
231
+ {%- elif message['content'] is string -%}
232
+ {%- if 'name' in message -%}
233
+ {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
234
+ {%- else -%}
235
+ {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
236
+ {%- endif -%}
237
+ {%- elif message['content'] is sequence -%}
238
+ {%- for item in message['content'] -%}
239
+ {%- if item is mapping -%}
240
+ {%- if 'name' in item and 'response' in item -%}
241
+ {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
242
+ {%- set response_ns = namespace(found_first=false) -%}
243
+ {%- for key, value in item['response'] | dictsort -%}
244
+ {%- if response_ns.found_first %},{% endif -%}
245
+ {%- set response_ns.found_first = true -%}
246
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
247
+ {%- endfor -%}
248
+ {{- '}<end_function_response>' -}}
249
+ {%- elif 'name' in message -%}
250
+ {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
251
+ {%- set response_ns = namespace(found_first=false) -%}
252
+ {%- for key, value in item | dictsort -%}
253
+ {%- if response_ns.found_first %},{% endif -%}
254
+ {%- set response_ns.found_first = true -%}
255
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
256
+ {%- endfor -%}
257
+ {{- '}<end_function_response>' -}}
258
+ {%- else -%}
259
+ {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
260
+ {%- endif -%}
261
+ {%- else -%}
262
+ {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
263
+ {%- endif -%}
264
+ {%- endfor -%}
265
+ {%- else -%}
266
+ {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
267
+ {%- endif -%}
268
+ {%- endif -%}
269
+ {%- set ns.prev_message_type = 'tool_response' -%}
270
+ {%- endif -%}
271
+ {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
272
+ {{ '<end_of_turn>\n' }}
273
+ {%- endif -%}
274
+ {%- endfor -%}
275
+ {%- if add_generation_prompt -%}
276
+ {%- if ns.prev_message_type != 'tool_response' -%}
277
+ {{- '<start_of_turn>model\n' -}}
278
+ {%- endif -%}
279
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modelName": "functiongemma-270m-it",
3
+ "modelFamily": "functiongemma",
4
+ "format": "coreml-mlprogram",
5
+ "architecture": "ane_unified_state",
6
+ "source": "huggingface",
7
+ "hfRepo": "google/functiongemma-270m-it",
8
+ "tSpecs": [
9
+ 1,
10
+ 128
11
+ ],
12
+ "cacheSeqLen": 128,
13
+ "numLayers": 18,
14
+ "numKvHeads": 1,
15
+ "headDim": 256,
16
+ "hiddenSize": 640,
17
+ "computePrecision": "float16",
18
+ "quantization": "none",
19
+ "computeUnits": "cpu_and_ne",
20
+ "stateNames": [
21
+ "k_cache_0",
22
+ "v_cache_0",
23
+ "k_cache_1",
24
+ "v_cache_1",
25
+ "k_cache_2",
26
+ "v_cache_2",
27
+ "k_cache_3",
28
+ "v_cache_3",
29
+ "k_cache_4",
30
+ "v_cache_4",
31
+ "k_cache_5",
32
+ "v_cache_5",
33
+ "k_cache_6",
34
+ "v_cache_6",
35
+ "k_cache_7",
36
+ "v_cache_7",
37
+ "k_cache_8",
38
+ "v_cache_8",
39
+ "k_cache_9",
40
+ "v_cache_9",
41
+ "k_cache_10",
42
+ "v_cache_10",
43
+ "k_cache_11",
44
+ "v_cache_11",
45
+ "k_cache_12",
46
+ "v_cache_12",
47
+ "k_cache_13",
48
+ "v_cache_13",
49
+ "k_cache_14",
50
+ "v_cache_14",
51
+ "k_cache_15",
52
+ "v_cache_15",
53
+ "k_cache_16",
54
+ "v_cache_16",
55
+ "k_cache_17",
56
+ "v_cache_17"
57
+ ],
58
+ "requires": {
59
+ "minimumDeploymentTarget": "iOS 18 / macOS 15",
60
+ "feature": "ANE BC1S unified + MLState"
61
+ },
62
+ "inputs": [
63
+ "input_ids",
64
+ "cos_full",
65
+ "sin_full",
66
+ "cos_sliding",
67
+ "sin_sliding",
68
+ "write_mask",
69
+ "attention_mask",
70
+ "logits_mask"
71
+ ],
72
+ "outputs": [
73
+ "logits"
74
+ ]
75
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
3
+ size 33384898
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "boi_token": "<start_of_image>",
4
+ "bos_token": "<bos>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eoi_token": "<end_of_image>",
7
+ "eos_token": "<eos>",
8
+ "image_token": "<image_soft_token>",
9
+ "is_local": false,
10
+ "local_files_only": false,
11
+ "mask_token": "<mask>",
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "model_specific_special_tokens": {
14
+ "boi_token": "<start_of_image>",
15
+ "eoi_token": "<end_of_image>",
16
+ "image_token": "<image_soft_token>",
17
+ "sfr_token": "<start_function_response>"
18
+ },
19
+ "pad_token": "<pad>",
20
+ "padding_side": "left",
21
+ "sfr_token": "<start_function_response>",
22
+ "sp_model_kwargs": null,
23
+ "spaces_between_special_tokens": false,
24
+ "tokenizer_class": "GemmaTokenizer",
25
+ "unk_token": "<unk>",
26
+ "use_default_system_prompt": false
27
+ }