dealign.ai - MLX Studio - JANG_Quant commited on
Commit
0e632c5
·
1 Parent(s): 8b4ba67

Restore all files + update README v2

Browse files
.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
chat_template.jinja ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- set add_comma = false -%}
6
+ {%- if key not in standard_keys -%}
7
+ {%- if ns.found_first %},{% endif -%}
8
+ {%- set ns.found_first = true -%}
9
+ {{ key }}:{
10
+ {%- if value['description'] -%}
11
+ description:<|"|>{{ value['description'] }}<|"|>
12
+ {%- set add_comma = true -%}
13
+ {%- endif -%}
14
+ {%- if value['nullable'] %}
15
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
16
+ nullable:true
17
+ {%- endif -%}
18
+ {%- if value['type'] | upper == 'STRING' -%}
19
+ {%- if value['enum'] -%}
20
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
21
+ enum:{{ format_argument(value['enum']) }}
22
+ {%- endif -%}
23
+ {%- elif value['type'] | upper == 'OBJECT' -%}
24
+ ,properties:{
25
+ {%- if value['properties'] is defined and value['properties'] is mapping -%}
26
+ {{- format_parameters(value['properties'], value['required'] | default([])) -}}
27
+ {%- elif value is mapping -%}
28
+ {{- format_parameters(value, value['required'] | default([])) -}}
29
+ {%- endif -%}
30
+ }
31
+ {%- if value['required'] -%}
32
+ ,required:[
33
+ {%- for item in value['required'] | default([]) -%}
34
+ <|"|>{{- item -}}<|"|>
35
+ {%- if not loop.last %},{% endif -%}
36
+ {%- endfor -%}
37
+ ]
38
+ {%- endif -%}
39
+ {%- elif value['type'] | upper == 'ARRAY' -%}
40
+ {%- if value['items'] is mapping and value['items'] -%}
41
+ ,items:{
42
+ {%- set ns_items = namespace(found_first=false) -%}
43
+ {%- for item_key, item_value in value['items'] | dictsort -%}
44
+ {%- if item_value is not none -%}
45
+ {%- if ns_items.found_first %},{% endif -%}
46
+ {%- set ns_items.found_first = true -%}
47
+ {%- if item_key == 'properties' -%}
48
+ properties:{
49
+ {%- if item_value is mapping -%}
50
+ {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
51
+ {%- endif -%}
52
+ }
53
+ {%- elif item_key == 'required' -%}
54
+ required:[
55
+ {%- for req_item in item_value -%}
56
+ <|"|>{{- req_item -}}<|"|>
57
+ {%- if not loop.last %},{% endif -%}
58
+ {%- endfor -%}
59
+ ]
60
+ {%- elif item_key == 'type' -%}
61
+ {%- if item_value is string -%}
62
+ type:{{ format_argument(item_value | upper) }}
63
+ {%- else -%}
64
+ type:{{ format_argument(item_value | map('upper') | list) }}
65
+ {%- endif -%}
66
+ {%- else -%}
67
+ {{ item_key }}:{{ format_argument(item_value) }}
68
+ {%- endif -%}
69
+ {%- endif -%}
70
+ {%- endfor -%}
71
+ }
72
+ {%- endif -%}
73
+ {%- endif -%}
74
+ {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
75
+ type:<|"|>{{ value['type'] | upper }}<|"|>}
76
+ {%- endif -%}
77
+ {%- endfor -%}
78
+ {%- endmacro -%}
79
+ {%- macro format_function_declaration(tool_data) -%}
80
+ declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
81
+ {%- set params = tool_data['function']['parameters'] -%}
82
+ {%- if params -%}
83
+ ,parameters:{
84
+ {%- if params['properties'] -%}
85
+ properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
86
+ {%- endif -%}
87
+ {%- if params['required'] -%}
88
+ required:[
89
+ {%- for item in params['required'] -%}
90
+ <|"|>{{- item -}}<|"|>
91
+ {{- ',' if not loop.last -}}
92
+ {%- endfor -%}
93
+ ],
94
+ {%- endif -%}
95
+ {%- if params['type'] -%}
96
+ type:<|"|>{{- params['type'] | upper -}}<|"|>}
97
+ {%- endif -%}
98
+ {%- endif -%}
99
+ {%- if 'response' in tool_data['function'] -%}
100
+ {%- set response_declaration = tool_data['function']['response'] -%}
101
+ ,response:{
102
+ {%- if response_declaration['description'] -%}
103
+ description:<|"|>{{- response_declaration['description'] -}}<|"|>,
104
+ {%- endif -%}
105
+ {%- if response_declaration['type'] | upper == 'OBJECT' -%}
106
+ type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
107
+ {%- endif -%}
108
+ {%- endif -%}
109
+ }
110
+ {%- endmacro -%}
111
+ {%- macro format_argument(argument, escape_keys=True) -%}
112
+ {%- if argument is string -%}
113
+ {{- '<|"|>' + argument + '<|"|>' -}}
114
+ {%- elif argument is boolean -%}
115
+ {{- 'true' if argument else 'false' -}}
116
+ {%- elif argument is mapping -%}
117
+ {{- '{' -}}
118
+ {%- set ns = namespace(found_first=false) -%}
119
+ {%- for key, value in argument | dictsort -%}
120
+ {%- if ns.found_first %},{% endif -%}
121
+ {%- set ns.found_first = true -%}
122
+ {%- if escape_keys -%}
123
+ {{- '<|"|>' + key + '<|"|>' -}}
124
+ {%- else -%}
125
+ {{- key -}}
126
+ {%- endif -%}
127
+ :{{- format_argument(value, escape_keys=escape_keys) -}}
128
+ {%- endfor -%}
129
+ {{- '}' -}}
130
+ {%- elif argument is sequence -%}
131
+ {{- '[' -}}
132
+ {%- for item in argument -%}
133
+ {{- format_argument(item, escape_keys=escape_keys) -}}
134
+ {%- if not loop.last %},{% endif -%}
135
+ {%- endfor -%}
136
+ {{- ']' -}}
137
+ {%- else -%}
138
+ {{- argument -}}
139
+ {%- endif -%}
140
+ {%- endmacro -%}
141
+ {%- macro strip_thinking(text) -%}
142
+ {%- set ns = namespace(result='') -%}
143
+ {%- for part in text.split('<channel|>') -%}
144
+ {%- if '<|channel>' in part -%}
145
+ {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
146
+ {%- else -%}
147
+ {%- set ns.result = ns.result + part -%}
148
+ {%- endif -%}
149
+ {%- endfor -%}
150
+ {{- ns.result | trim -}}
151
+ {%- endmacro -%}
152
+
153
+ {%- set ns = namespace(prev_message_type=None) -%}
154
+ {%- set loop_messages = messages -%}
155
+ {{ bos_token }}
156
+ {#- Handle System/Tool Definitions Block -#}
157
+ {%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
158
+ {{- '<|turn>system\n' -}}
159
+
160
+ {#- Inject Thinking token at the very top of the FIRST system turn -#}
161
+ {%- if enable_thinking is defined and enable_thinking -%}
162
+ {{- '<|think|>' -}}
163
+ {%- set ns.prev_message_type = 'think' -%}
164
+ {%- endif -%}
165
+
166
+ {%- if messages[0]['role'] in ['system', 'developer'] -%}
167
+ {{- messages[0]['content'] | trim -}}
168
+ {%- set loop_messages = messages[1:] -%}
169
+ {%- endif -%}
170
+
171
+ {%- if tools -%}
172
+ {%- for tool in tools %}
173
+ {{- '<|tool>' -}}
174
+ {{- format_function_declaration(tool) | trim -}}
175
+ {{- '<tool|>' -}}
176
+ {%- endfor %}
177
+ {%- set ns.prev_message_type = 'tool' -%}
178
+ {%- endif -%}
179
+
180
+ {{- '<turn|>\n' -}}
181
+ {%- endif %}
182
+
183
+ {#- Loop through messages -#}
184
+ {%- for message in loop_messages -%}
185
+ {%- set ns.prev_message_type = None -%}
186
+ {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
187
+ {{- '<|turn>' + role + '\n' }}
188
+
189
+ {%- if message['tool_calls'] -%}
190
+ {%- for tool_call in message['tool_calls'] -%}
191
+ {%- set function = tool_call['function'] -%}
192
+ {{- '<|tool_call>call:' + function['name'] + '{' -}}
193
+ {%- if function['arguments'] is mapping -%}
194
+ {%- set ns_args = namespace(found_first=false) -%}
195
+ {%- for key, value in function['arguments'] | dictsort -%}
196
+ {%- if ns_args.found_first %},{% endif -%}
197
+ {%- set ns_args.found_first = true -%}
198
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
199
+ {%- endfor -%}
200
+ {%- elif function['arguments'] is string -%}
201
+ {{- function['arguments'] -}}
202
+ {%- endif -%}
203
+ {{- '}<tool_call|>' -}}
204
+ {%- endfor -%}
205
+ {%- set ns.prev_message_type = 'tool_call' -%}
206
+ {%- endif -%}
207
+
208
+ {%- if message['tool_responses'] -%}
209
+ {#- Tool Response handling -#}
210
+ {%- for tool_response in message['tool_responses'] -%}
211
+ {{- '<|tool_response>' -}}
212
+ {%- if tool_response['response'] is mapping -%}
213
+ {{- 'response:' + tool_response['name'] | default('unknown') + '{' -}}
214
+ {%- for key, value in tool_response['response'] | dictsort -%}
215
+ {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
216
+ {%- if not loop.last %},{% endif -%}
217
+ {%- endfor -%}
218
+ {{- '}' -}}
219
+ {%- else -%}
220
+ {{- 'response:' + tool_response['name'] | default('unknown') + '{value:' + format_argument(tool_response['response'], escape_keys=False) + '}' -}}
221
+ {%- endif -%}
222
+ {{- '<tool_response|>' -}}
223
+ {%- endfor -%}
224
+ {%- set ns.prev_message_type = 'tool_response' -%}
225
+ {%- endif -%}
226
+
227
+ {%- if message['content'] is string -%}
228
+ {%- if role == 'model' -%}
229
+ {{- strip_thinking(message['content']) -}}
230
+ {%- else -%}
231
+ {{- message['content'] | trim -}}
232
+ {%- endif -%}
233
+ {%- elif message['content'] is sequence -%}
234
+ {%- for item in message['content'] -%}
235
+ {%- if item['type'] == 'text' -%}
236
+ {%- if role == 'model' -%}
237
+ {{- strip_thinking(item['text']) -}}
238
+ {%- else -%}
239
+ {{- item['text'] | trim -}}
240
+ {%- endif -%}
241
+ {%- elif item['type'] == 'image' -%}
242
+ {{- '\n\n<|image|>\n\n' -}}
243
+ {%- set ns.prev_message_type = 'image' -%}
244
+ {%- elif item['type'] == 'audio' -%}
245
+ {{- '<|audio|>' -}}
246
+ {%- set ns.prev_message_type = 'audio' -%}
247
+ {%- elif item['type'] == 'video' -%}
248
+ {{- '\n\n<|video|>\n\n' -}}
249
+ {%- set ns.prev_message_type = 'video' -%}
250
+ {%- endif -%}
251
+ {%- endfor -%}
252
+ {%- endif -%}
253
+
254
+ {%- if not (message['tool_responses'] and not message['content']) -%}
255
+ {{- '<turn|>\n' -}}
256
+ {%- endif -%}
257
+ {%- endfor -%}
258
+
259
+ {%- if add_generation_prompt -%}
260
+ {%- if ns.prev_message_type != 'tool_response' -%}
261
+ {{- '<|turn>model\n' -}}
262
+ {%- endif -%}
263
+ {%- if not enable_thinking | default(false) -%}
264
+ {{- '<|channel>thought\n<channel|>' -}}
265
+ {%- endif -%}
266
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_token_id": 258881,
6
+ "boa_token_id": 256000,
7
+ "boi_token_id": 255999,
8
+ "dtype": "bfloat16",
9
+ "eoa_token_id": 258883,
10
+ "eoa_token_index": 258883,
11
+ "eoi_token_id": 258882,
12
+ "eos_token_id": [
13
+ 1,
14
+ 106
15
+ ],
16
+ "image_token_id": 258880,
17
+ "initializer_range": 0.02,
18
+ "model_type": "gemma4",
19
+ "text_config": {
20
+ "attention_bias": false,
21
+ "attention_dropout": 0.0,
22
+ "attention_k_eq_v": true,
23
+ "bos_token_id": 2,
24
+ "dtype": "bfloat16",
25
+ "enable_moe_block": false,
26
+ "eos_token_id": 1,
27
+ "expert_intermediate_size": null,
28
+ "final_logit_softcapping": 30.0,
29
+ "global_head_dim": 512,
30
+ "head_dim": 256,
31
+ "hidden_activation": "gelu_pytorch_tanh",
32
+ "hidden_size": 5376,
33
+ "hidden_size_per_layer_input": 0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 21504,
36
+ "layer_types": [
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "full_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "full_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "full_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "full_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "full_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "full_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "full_attention"
97
+ ],
98
+ "max_position_embeddings": 262144,
99
+ "model_type": "gemma4_text",
100
+ "num_attention_heads": 32,
101
+ "num_experts": null,
102
+ "num_global_key_value_heads": 4,
103
+ "num_hidden_layers": 60,
104
+ "num_key_value_heads": 16,
105
+ "num_kv_shared_layers": 0,
106
+ "pad_token_id": 0,
107
+ "rms_norm_eps": 1e-06,
108
+ "rope_parameters": {
109
+ "full_attention": {
110
+ "partial_rotary_factor": 0.25,
111
+ "rope_theta": 1000000.0,
112
+ "rope_type": "proportional"
113
+ },
114
+ "sliding_attention": {
115
+ "rope_theta": 10000.0,
116
+ "rope_type": "default"
117
+ }
118
+ },
119
+ "sliding_window": 1024,
120
+ "tie_word_embeddings": true,
121
+ "top_k_experts": null,
122
+ "use_bidirectional_attention": "vision",
123
+ "use_cache": true,
124
+ "use_double_wide_mlp": false,
125
+ "vocab_size": 262144,
126
+ "vocab_size_per_layer_input": 262144
127
+ },
128
+ "tie_word_embeddings": true,
129
+ "transformers_version": "5.5.0.dev0",
130
+ "video_token_id": 258884,
131
+ "vision_config": {
132
+ "_name_or_path": "",
133
+ "architectures": null,
134
+ "attention_bias": false,
135
+ "attention_dropout": 0.0,
136
+ "chunk_size_feed_forward": 0,
137
+ "default_output_length": 280,
138
+ "dtype": "bfloat16",
139
+ "global_head_dim": 72,
140
+ "head_dim": 72,
141
+ "hidden_activation": "gelu_pytorch_tanh",
142
+ "hidden_size": 1152,
143
+ "id2label": {
144
+ "0": "LABEL_0",
145
+ "1": "LABEL_1"
146
+ },
147
+ "initializer_range": 0.02,
148
+ "intermediate_size": 4304,
149
+ "is_encoder_decoder": false,
150
+ "label2id": {
151
+ "LABEL_0": 0,
152
+ "LABEL_1": 1
153
+ },
154
+ "max_position_embeddings": 131072,
155
+ "model_type": "gemma4_vision",
156
+ "num_attention_heads": 16,
157
+ "num_hidden_layers": 27,
158
+ "num_key_value_heads": 16,
159
+ "output_attentions": false,
160
+ "output_hidden_states": false,
161
+ "patch_size": 16,
162
+ "pooling_kernel_size": 3,
163
+ "position_embedding_size": 10240,
164
+ "problem_type": null,
165
+ "return_dict": true,
166
+ "rms_norm_eps": 1e-06,
167
+ "rope_parameters": {
168
+ "rope_theta": 100.0,
169
+ "rope_type": "default"
170
+ },
171
+ "standardize": true,
172
+ "use_clipped_linears": false
173
+ },
174
+ "vision_soft_tokens_per_image": 280,
175
+ "quantization": {
176
+ "group_size": 64,
177
+ "bits": 4
178
+ }
179
+ }
dealign_logo.png ADDED
dealign_mascot.png ADDED
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106,
7
+ 50
8
+ ],
9
+ "pad_token_id": 0,
10
+ "temperature": 1.0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "5.5.0.dev0"
14
+ }
jang_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "quantization": {
3
+ "method": "jang-importance",
4
+ "profile": "JANG_4M",
5
+ "target_bits": 4.0,
6
+ "actual_bits": 5.1,
7
+ "block_size": 64,
8
+ "calibration_method": "weights",
9
+ "quantization_method": "mse",
10
+ "scoring_method": "weight-magnitude",
11
+ "bit_widths_used": [
12
+ 4,
13
+ 8
14
+ ],
15
+ "quantization_scheme": "asymmetric",
16
+ "quantization_backend": "mx.quantize"
17
+ },
18
+ "source_model": {
19
+ "name": "Gemma-4-31B-it-BF16",
20
+ "dtype": "bfloat16",
21
+ "parameters": "29.2B"
22
+ },
23
+ "architecture": {
24
+ "type": "transformer",
25
+ "attention": "gqa",
26
+ "has_vision": true,
27
+ "has_ssm": false,
28
+ "has_moe": false
29
+ },
30
+ "runtime": {
31
+ "total_weight_bytes": 19586875392,
32
+ "total_weight_gb": 18.24
33
+ },
34
+ "format": "jang",
35
+ "format_version": "2.0",
36
+ "crack_surgery": {
37
+ "method": "per-layer",
38
+ "mode": "mpoa",
39
+ "vector": "gemma4_31b_refusal_vectors.safetensors",
40
+ "target_layers": [
41
+ 20,
42
+ 21,
43
+ 22,
44
+ 23,
45
+ 24,
46
+ 25,
47
+ 26,
48
+ 27,
49
+ 28,
50
+ 29,
51
+ 30,
52
+ 31,
53
+ 32,
54
+ 33,
55
+ 34,
56
+ 35,
57
+ 36,
58
+ 37,
59
+ 38,
60
+ 39,
61
+ 40,
62
+ 41,
63
+ 42,
64
+ 43,
65
+ 44,
66
+ 45,
67
+ 46,
68
+ 47,
69
+ 48,
70
+ 49
71
+ ],
72
+ "target_projs": [
73
+ "o_proj",
74
+ "down_proj"
75
+ ],
76
+ "strength": 1.2,
77
+ "modified_tensors": 60
78
+ }
79
+ }
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_ms_per_token": 40,
3
+ "audio_seq_length": 750,
4
+ "feature_extractor": {
5
+ "dither": 0.0,
6
+ "feature_extractor_type": "Gemma4AudioFeatureExtractor",
7
+ "feature_size": 128,
8
+ "fft_length": 512,
9
+ "fft_overdrive": false,
10
+ "frame_length": 320,
11
+ "hop_length": 160,
12
+ "input_scale_factor": 1.0,
13
+ "max_frequency": 8000.0,
14
+ "mel_floor": 0.001,
15
+ "min_frequency": 0.0,
16
+ "padding_side": "right",
17
+ "padding_value": 0.0,
18
+ "per_bin_mean": null,
19
+ "per_bin_stddev": null,
20
+ "preemphasis": 0.0,
21
+ "preemphasis_htk_flavor": true,
22
+ "return_attention_mask": true,
23
+ "sampling_rate": 16000
24
+ },
25
+ "image_processor": {
26
+ "do_convert_rgb": true,
27
+ "do_normalize": false,
28
+ "do_rescale": true,
29
+ "do_resize": true,
30
+ "image_mean": [
31
+ 0.0,
32
+ 0.0,
33
+ 0.0
34
+ ],
35
+ "image_processor_type": "Gemma4ImageProcessor",
36
+ "image_seq_length": 280,
37
+ "image_std": [
38
+ 1.0,
39
+ 1.0,
40
+ 1.0
41
+ ],
42
+ "max_soft_tokens": 280,
43
+ "patch_size": 16,
44
+ "pooling_kernel_size": 3,
45
+ "resample": 3,
46
+ "rescale_factor": 0.00392156862745098
47
+ },
48
+ "image_seq_length": 280,
49
+ "processor_class": "Gemma4Processor",
50
+ "video_processor": {
51
+ "do_convert_rgb": true,
52
+ "do_normalize": true,
53
+ "do_rescale": true,
54
+ "do_resize": true,
55
+ "do_sample_frames": true,
56
+ "image_mean": [
57
+ 0.0,
58
+ 0.0,
59
+ 0.0
60
+ ],
61
+ "image_std": [
62
+ 1.0,
63
+ 1.0,
64
+ 1.0
65
+ ],
66
+ "max_soft_tokens": 70,
67
+ "num_frames": 32,
68
+ "patch_size": 16,
69
+ "pooling_kernel_size": 3,
70
+ "resample": 3,
71
+ "rescale_factor": 0.00392156862745098,
72
+ "return_metadata": false,
73
+ "video_processor_type": "Gemma4VideoProcessor"
74
+ }
75
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3151898c022536cf420b732dd2fcbf8e7c456cd39711a27f9b82a7ced72b6c83
3
+ size 32169627
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_token": "<|audio|>",
3
+ "backend": "tokenizers",
4
+ "boa_token": "<|audio>",
5
+ "boi_token": "<|image>",
6
+ "bos_token": "<bos>",
7
+ "eoa_token": "<audio|>",
8
+ "eoc_token": "<channel|>",
9
+ "eoi_token": "<image|>",
10
+ "eos_token": "<eos>",
11
+ "eot_token": "<turn|>",
12
+ "escape_token": "<|\"|>",
13
+ "etc_token": "<tool_call|>",
14
+ "etd_token": "<tool|>",
15
+ "etr_token": "<tool_response|>",
16
+ "extra_special_tokens": [
17
+ "<|video|>"
18
+ ],
19
+ "image_token": "<|image|>",
20
+ "mask_token": "<mask>",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": "<pad>",
23
+ "padding_side": "left",
24
+ "processor_class": "Gemma4Processor",
25
+ "response_schema": {
26
+ "type": "object",
27
+ "properties": {
28
+ "role": {
29
+ "const": "assistant"
30
+ },
31
+ "thinking": {
32
+ "type": "string"
33
+ },
34
+ "content": {
35
+ "type": "string"
36
+ },
37
+ "tool_calls": {
38
+ "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
39
+ "type": "array",
40
+ "items": {
41
+ "type": "object",
42
+ "properties": {
43
+ "type": {
44
+ "const": "function"
45
+ },
46
+ "function": {
47
+ "type": "object",
48
+ "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
49
+ "properties": {
50
+ "name": {
51
+ "type": "string"
52
+ },
53
+ "arguments": {
54
+ "type": "object",
55
+ "x-parser": "gemma4-tool-call",
56
+ "additionalProperties": {}
57
+ }
58
+ }
59
+ }
60
+ }
61
+ }
62
+ }
63
+ },
64
+ "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
65
+ },
66
+ "soc_token": "<|channel>",
67
+ "sot_token": "<|turn>",
68
+ "stc_token": "<|tool_call>",
69
+ "std_token": "<|tool>",
70
+ "str_token": "<|tool_response>",
71
+ "think_token": "<|think|>",
72
+ "tokenizer_class": "GemmaTokenizer",
73
+ "unk_token": "<unk>"
74
+ }
vmlx-banner.png ADDED