prince-canuma commited on
Commit
b16892b
·
verified ·
1 Parent(s): 75ffc87

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
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: mlx
3
+ license: apache-2.0
4
+ license_link: https://ai.google.dev/gemma/docs/gemma_4_license
5
+ pipeline_tag: any-to-any
6
+ base_model: google/gemma-4-e2b-it
7
+ tags:
8
+ - mlx
9
+ ---
10
+
11
+ # mlx-community/gemma-4-e2b-it-bf16
12
+
13
+ This model was converted to MLX format from [`google/gemma-4-e2b-it`](https://huggingface.co/google/gemma-4-e2b-it)
14
+ using mlx-vlm version **0.4.3**.
15
+ Refer to the [original model card](https://huggingface.co/google/gemma-4-e2b-it) for more details on the model.
16
+
17
+ ## Use with mlx
18
+
19
+ ```bash
20
+ pip install -U mlx-vlm
21
+ ```
22
+
23
+ ```bash
24
+ python -m mlx_vlm.generate --model mlx-community/gemma-4-e2b-it-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
25
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_config": {
6
+ "_name_or_path": "",
7
+ "architectures": null,
8
+ "attention_chunk_size": 12,
9
+ "attention_context_left": 13,
10
+ "attention_context_right": 0,
11
+ "attention_invalid_logits_value": -1000000000.0,
12
+ "attention_logit_cap": 50.0,
13
+ "chunk_size_feed_forward": 0,
14
+ "conv_kernel_size": 5,
15
+ "dtype": "bfloat16",
16
+ "gradient_clipping": 10000000000.0,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 1024,
19
+ "id2label": {
20
+ "0": "LABEL_0",
21
+ "1": "LABEL_1"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "is_encoder_decoder": false,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1
28
+ },
29
+ "model_type": "gemma4_audio",
30
+ "num_attention_heads": 8,
31
+ "num_hidden_layers": 12,
32
+ "output_attentions": false,
33
+ "output_hidden_states": false,
34
+ "output_proj_dims": 1536,
35
+ "problem_type": null,
36
+ "residual_weight": 0.5,
37
+ "return_dict": true,
38
+ "rms_norm_eps": 1e-06,
39
+ "subsampling_conv_channels": [
40
+ 128,
41
+ 32
42
+ ],
43
+ "use_clipped_linears": true
44
+ },
45
+ "audio_token_id": 258881,
46
+ "boa_token_id": 256000,
47
+ "boi_token_id": 255999,
48
+ "dtype": "bfloat16",
49
+ "eoa_token_id": 258883,
50
+ "eoa_token_index": 258883,
51
+ "eoi_token_id": 258882,
52
+ "eos_token_id": [
53
+ 1,
54
+ 106,
55
+ 50
56
+ ],
57
+ "image_token_id": 258880,
58
+ "initializer_range": 0.02,
59
+ "model_type": "gemma4",
60
+ "text_config": {
61
+ "attention_bias": false,
62
+ "attention_dropout": 0.0,
63
+ "attention_k_eq_v": false,
64
+ "bos_token_id": 2,
65
+ "dtype": "bfloat16",
66
+ "enable_moe_block": false,
67
+ "eos_token_id": 1,
68
+ "expert_intermediate_size": null,
69
+ "final_logit_softcapping": 30.0,
70
+ "global_head_dim": 512,
71
+ "head_dim": 256,
72
+ "hidden_activation": "gelu_pytorch_tanh",
73
+ "hidden_size": 1536,
74
+ "hidden_size_per_layer_input": 256,
75
+ "initializer_range": 0.02,
76
+ "intermediate_size": 6144,
77
+ "layer_types": [
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "full_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "full_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "full_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "full_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "full_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "sliding_attention",
107
+ "full_attention",
108
+ "sliding_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "full_attention"
113
+ ],
114
+ "max_position_embeddings": 131072,
115
+ "model_type": "gemma4_text",
116
+ "num_attention_heads": 8,
117
+ "num_experts": null,
118
+ "num_global_key_value_heads": null,
119
+ "num_hidden_layers": 35,
120
+ "num_key_value_heads": 1,
121
+ "num_kv_shared_layers": 20,
122
+ "pad_token_id": 0,
123
+ "rms_norm_eps": 1e-06,
124
+ "rope_parameters": {
125
+ "full_attention": {
126
+ "partial_rotary_factor": 0.25,
127
+ "rope_theta": 1000000.0,
128
+ "rope_type": "proportional"
129
+ },
130
+ "sliding_attention": {
131
+ "rope_theta": 10000.0,
132
+ "rope_type": "default"
133
+ }
134
+ },
135
+ "sliding_window": 512,
136
+ "tie_word_embeddings": true,
137
+ "top_k_experts": null,
138
+ "use_bidirectional_attention": null,
139
+ "use_cache": true,
140
+ "use_double_wide_mlp": true,
141
+ "vocab_size": 262144,
142
+ "vocab_size_per_layer_input": 262144
143
+ },
144
+ "tie_word_embeddings": true,
145
+ "transformers_version": "5.5.0.dev0",
146
+ "video_token_id": 258884,
147
+ "vision_config": {
148
+ "_name_or_path": "",
149
+ "architectures": null,
150
+ "attention_bias": false,
151
+ "attention_dropout": 0.0,
152
+ "chunk_size_feed_forward": 0,
153
+ "default_output_length": 280,
154
+ "dtype": "bfloat16",
155
+ "global_head_dim": 64,
156
+ "head_dim": 64,
157
+ "hidden_activation": "gelu_pytorch_tanh",
158
+ "hidden_size": 768,
159
+ "id2label": {
160
+ "0": "LABEL_0",
161
+ "1": "LABEL_1"
162
+ },
163
+ "initializer_range": 0.02,
164
+ "intermediate_size": 3072,
165
+ "is_encoder_decoder": false,
166
+ "label2id": {
167
+ "LABEL_0": 0,
168
+ "LABEL_1": 1
169
+ },
170
+ "max_position_embeddings": 131072,
171
+ "model_type": "gemma4_vision",
172
+ "num_attention_heads": 12,
173
+ "num_hidden_layers": 16,
174
+ "num_key_value_heads": 12,
175
+ "output_attentions": false,
176
+ "output_hidden_states": false,
177
+ "patch_size": 16,
178
+ "pooling_kernel_size": 3,
179
+ "position_embedding_size": 10240,
180
+ "problem_type": null,
181
+ "return_dict": true,
182
+ "rms_norm_eps": 1e-06,
183
+ "rope_parameters": {
184
+ "rope_theta": 100.0,
185
+ "rope_type": "default"
186
+ },
187
+ "standardize": false,
188
+ "use_clipped_linears": true
189
+ },
190
+ "vision_soft_tokens_per_image": 280
191
+ }
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
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff4c28c7f1b0a841697cdd10fc7b45d434c2edeb6e02360e8a56ed88fa7b1cef
3
+ size 4569831590
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d44b0ee3454db90d6d10b4006b0270be0729094809570c9b366f3a35ca7655
3
+ size 5366705230
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb5cbee871ebe7dcfaebef771c3013dd6cee51d9c8e0023d5d7c32cb0e9e244
3
+ size 310074804
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_seq_length": 750,
3
+ "image_processor": {
4
+ "do_convert_rgb": true,
5
+ "do_normalize": false,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.0,
10
+ 0.0,
11
+ 0.0
12
+ ],
13
+ "image_processor_type": "Gemma4ImageProcessor",
14
+ "image_seq_length": 280,
15
+ "image_std": [
16
+ 1.0,
17
+ 1.0,
18
+ 1.0
19
+ ],
20
+ "max_soft_tokens": 280,
21
+ "patch_size": 16,
22
+ "pooling_kernel_size": 3,
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 224,
27
+ "width": 224
28
+ }
29
+ },
30
+ "image_seq_length": 280,
31
+ "processor_class": "Gemma4Processor"
32
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
3
+ size 32169626
tokenizer_config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": true,
21
+ "mask_token": "<mask>",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "model_specific_special_tokens": {
24
+ "audio_token": "<|audio|>",
25
+ "boa_token": "<|audio>",
26
+ "boi_token": "<|image>",
27
+ "eoa_token": "<audio|>",
28
+ "eoc_token": "<channel|>",
29
+ "eoi_token": "<image|>",
30
+ "eot_token": "<turn|>",
31
+ "escape_token": "<|\"|>",
32
+ "etc_token": "<tool_call|>",
33
+ "etd_token": "<tool|>",
34
+ "etr_token": "<tool_response|>",
35
+ "image_token": "<|image|>",
36
+ "soc_token": "<|channel>",
37
+ "sot_token": "<|turn>",
38
+ "stc_token": "<|tool_call>",
39
+ "std_token": "<|tool>",
40
+ "str_token": "<|tool_response>",
41
+ "think_token": "<|think|>"
42
+ },
43
+ "pad_token": "<pad>",
44
+ "padding_side": "left",
45
+ "processor_class": "Gemma4Processor",
46
+ "response_schema": {
47
+ "properties": {
48
+ "content": {
49
+ "type": "string"
50
+ },
51
+ "role": {
52
+ "const": "assistant"
53
+ },
54
+ "thinking": {
55
+ "type": "string"
56
+ },
57
+ "tool_calls": {
58
+ "items": {
59
+ "properties": {
60
+ "function": {
61
+ "properties": {
62
+ "arguments": {
63
+ "additionalProperties": {},
64
+ "type": "object",
65
+ "x-parser": "gemma4-tool-call"
66
+ },
67
+ "name": {
68
+ "type": "string"
69
+ }
70
+ },
71
+ "type": "object",
72
+ "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
73
+ },
74
+ "type": {
75
+ "const": "function"
76
+ }
77
+ },
78
+ "type": "object"
79
+ },
80
+ "type": "array",
81
+ "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
82
+ }
83
+ },
84
+ "type": "object",
85
+ "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
86
+ },
87
+ "soc_token": "<|channel>",
88
+ "sot_token": "<|turn>",
89
+ "stc_token": "<|tool_call>",
90
+ "std_token": "<|tool>",
91
+ "str_token": "<|tool_response>",
92
+ "think_token": "<|think|>",
93
+ "tokenizer_class": "GemmaTokenizer",
94
+ "unk_token": "<unk>"
95
+ }