Dexmal commited on
Commit
4c78b7f
·
verified ·
1 Parent(s): 9376017

Upload checkpoint

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
chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "action_config": {
3
+ "architectures": null,
4
+ "attention_bias": false,
5
+ "attention_dropout": 0.0,
6
+ "attn_implementation": "sdpa",
7
+ "attn_logit_softcapping": null,
8
+ "bos_token_id": 2,
9
+ "chunk_size_feed_forward": 0,
10
+ "dtype": null,
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 1024,
16
+ "id2label": {
17
+ "0": "LABEL_0",
18
+ "1": "LABEL_1"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "is_encoder_decoder": false,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1
26
+ },
27
+ "layer_types": [
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "full_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention"
62
+ ],
63
+ "max_position_embeddings": 131072,
64
+ "model_type": "gemma3_text",
65
+ "num_attention_heads": 8,
66
+ "num_hidden_layers": 34,
67
+ "num_key_value_heads": 4,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "pad_token_id": 0,
71
+ "problem_type": null,
72
+ "query_pre_attn_scalar": 256,
73
+ "return_dict": true,
74
+ "rms_norm_eps": 1e-06,
75
+ "rope_parameters": {
76
+ "full_attention": {
77
+ "factor": 8.0,
78
+ "rope_theta": 1000000.0,
79
+ "rope_type": "linear"
80
+ },
81
+ "sliding_attention": {
82
+ "rope_theta": 10000.0,
83
+ "rope_type": "default"
84
+ }
85
+ },
86
+ "sliding_window": 4096,
87
+ "tie_word_embeddings": true,
88
+ "use_bidirectional_attention": false,
89
+ "use_cache": true,
90
+ "vocab_size": 262208
91
+ },
92
+ "action_dim": 32,
93
+ "architectures": [
94
+ "DM05ForConditionalGeneration"
95
+ ],
96
+ "bos_token_id": 2,
97
+ "chunk_size": 50,
98
+ "dtype": "float32",
99
+ "eos_token_id": 1,
100
+ "model_type": "dm05",
101
+ "pad_token_id": 0,
102
+ "tie_word_embeddings": true,
103
+ "transformers_version": "5.3.0",
104
+ "use_cache": false,
105
+ "vlm_config": {
106
+ "architectures": [
107
+ "Gemma3ForConditionalGeneration"
108
+ ],
109
+ "attn_implementation": {
110
+ "": "flex_attention",
111
+ "text_config": "flex_attention",
112
+ "vision_config": "flash_attention_2"
113
+ },
114
+ "boi_token_index": 255999,
115
+ "chunk_size_feed_forward": 0,
116
+ "dtype": "bfloat16",
117
+ "eoi_token_index": 256000,
118
+ "eos_token_id": [
119
+ 1,
120
+ 106
121
+ ],
122
+ "id2label": {
123
+ "0": "LABEL_0",
124
+ "1": "LABEL_1"
125
+ },
126
+ "image_token_index": 262144,
127
+ "initializer_range": 0.02,
128
+ "is_encoder_decoder": false,
129
+ "label2id": {
130
+ "LABEL_0": 0,
131
+ "LABEL_1": 1
132
+ },
133
+ "mm_tokens_per_image": 256,
134
+ "model_type": "gemma3",
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "problem_type": null,
138
+ "return_dict": true,
139
+ "text_config": {
140
+ "architectures": null,
141
+ "attention_bias": false,
142
+ "attention_dropout": 0.0,
143
+ "attn_logit_softcapping": null,
144
+ "bos_token_id": 2,
145
+ "chunk_size_feed_forward": 0,
146
+ "dtype": "bfloat16",
147
+ "eos_token_id": 1,
148
+ "final_logit_softcapping": null,
149
+ "head_dim": 256,
150
+ "hidden_activation": "gelu_pytorch_tanh",
151
+ "hidden_size": 2560,
152
+ "id2label": {
153
+ "0": "LABEL_0",
154
+ "1": "LABEL_1"
155
+ },
156
+ "initializer_range": 0.02,
157
+ "intermediate_size": 10240,
158
+ "is_encoder_decoder": false,
159
+ "label2id": {
160
+ "LABEL_0": 0,
161
+ "LABEL_1": 1
162
+ },
163
+ "layer_types": [
164
+ "sliding_attention",
165
+ "sliding_attention",
166
+ "sliding_attention",
167
+ "sliding_attention",
168
+ "sliding_attention",
169
+ "full_attention",
170
+ "sliding_attention",
171
+ "sliding_attention",
172
+ "sliding_attention",
173
+ "sliding_attention",
174
+ "sliding_attention",
175
+ "full_attention",
176
+ "sliding_attention",
177
+ "sliding_attention",
178
+ "sliding_attention",
179
+ "sliding_attention",
180
+ "sliding_attention",
181
+ "full_attention",
182
+ "sliding_attention",
183
+ "sliding_attention",
184
+ "sliding_attention",
185
+ "sliding_attention",
186
+ "sliding_attention",
187
+ "full_attention",
188
+ "sliding_attention",
189
+ "sliding_attention",
190
+ "sliding_attention",
191
+ "sliding_attention",
192
+ "sliding_attention",
193
+ "full_attention",
194
+ "sliding_attention",
195
+ "sliding_attention",
196
+ "sliding_attention",
197
+ "sliding_attention"
198
+ ],
199
+ "max_position_embeddings": 131072,
200
+ "model_type": "gemma3_text",
201
+ "num_attention_heads": 8,
202
+ "num_hidden_layers": 34,
203
+ "num_key_value_heads": 4,
204
+ "output_attentions": false,
205
+ "output_hidden_states": false,
206
+ "pad_token_id": 0,
207
+ "problem_type": null,
208
+ "query_pre_attn_scalar": 256,
209
+ "return_dict": true,
210
+ "rms_norm_eps": 1e-06,
211
+ "rope_parameters": {
212
+ "full_attention": {
213
+ "factor": 8.0,
214
+ "rope_theta": 1000000.0,
215
+ "rope_type": "linear"
216
+ },
217
+ "sliding_attention": {
218
+ "rope_theta": 10000.0,
219
+ "rope_type": "default"
220
+ }
221
+ },
222
+ "sliding_window": 4096,
223
+ "tie_word_embeddings": true,
224
+ "use_bidirectional_attention": false,
225
+ "use_cache": true,
226
+ "vocab_size": 262208
227
+ },
228
+ "tie_word_embeddings": true,
229
+ "use_cache": false,
230
+ "vision_config": {
231
+ "architectures": null,
232
+ "attention_dropout": 0.0,
233
+ "chunk_size_feed_forward": 0,
234
+ "dtype": "bfloat16",
235
+ "hidden_act": "gelu_pytorch_tanh",
236
+ "hidden_size": 1152,
237
+ "id2label": {
238
+ "0": "LABEL_0",
239
+ "1": "LABEL_1"
240
+ },
241
+ "image_size": 448,
242
+ "intermediate_size": 4304,
243
+ "is_encoder_decoder": false,
244
+ "label2id": {
245
+ "LABEL_0": 0,
246
+ "LABEL_1": 1
247
+ },
248
+ "layer_norm_eps": 1e-06,
249
+ "model_type": "siglip_vision_model",
250
+ "num_attention_heads": 16,
251
+ "num_channels": 3,
252
+ "num_hidden_layers": 27,
253
+ "output_attentions": false,
254
+ "output_hidden_states": false,
255
+ "patch_size": 14,
256
+ "problem_type": null,
257
+ "return_dict": true,
258
+ "vision_use_head": false
259
+ }
260
+ }
261
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 0,
10
+ "transformers_version": "5.3.0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ca7d68d027074f5c554355a3ab92f347946e236fbe9330cb4f982151fe3352
3
+ size 23316655136
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_format": "channels_first",
3
+ "do_convert_rgb": null,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessorFast",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 448,
23
+ "width": 448
24
+ }
25
+ }
processor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": null,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Gemma3ImageProcessorFast",
14
+ "image_seq_length": 256,
15
+ "image_std": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 448,
24
+ "width": 448
25
+ }
26
+ },
27
+ "image_seq_length": 256,
28
+ "processor_class": "Gemma3Processor"
29
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
3
+ size 33384567
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": true,
10
+ "mask_token": "<mask>",
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "model_specific_special_tokens": {
13
+ "boi_token": "<start_of_image>",
14
+ "eoi_token": "<end_of_image>",
15
+ "image_token": "<image_soft_token>"
16
+ },
17
+ "pad_token": "<pad>",
18
+ "processor_class": "Gemma3Processor",
19
+ "sp_model_kwargs": null,
20
+ "spaces_between_special_tokens": false,
21
+ "tokenizer_class": "GemmaTokenizer",
22
+ "unk_token": "<unk>",
23
+ "use_default_system_prompt": false,
24
+ "image_token_id": 262144,
25
+ "boi_token_id": 255999,
26
+ "eoi_token_id": 256000
27
+ }