Hugging Face's logo

EZCon
/
gemma-3n-E2B-it-mlx

Image-Text-to-Text
Transformers
Safetensors
MLX
English
gemma3n
gemma3
unsloth
gemma
google
conversational
Model card Files
xet
Community
hermeschen-ezcon commited on
Commit
9a07efc
·
verified ·
1 Parent(s): 6b8ccf9

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. README.md +28 -0
  3. chat_template.jinja +49 -0
  4. config.json +430 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00003.safetensors +3 -0
  7. model-00002-of-00003.safetensors +3 -0
  8. model-00003-of-00003.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. preprocessor_config.json +51 -0
  11. processor_config.json +5 -0
  12. special_tokens_map.json +36 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +0 -0
.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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/gemma-3n-E2B-it
3
+ language:
4
+ - en
5
+ pipeline_tag: image-text-to-text
6
+ library_name: transformers
7
+ license: gemma
8
+ tags:
9
+ - gemma3
10
+ - unsloth
11
+ - transformers
12
+ - gemma
13
+ - google
14
+ - mlx
15
+ ---
16
+
17
+ # EZCon/gemma-3n-E2B-it-mlx
18
+ This model was converted to MLX format from [`unsloth/gemma-3n-E2B-it`]() using mlx-vlm version **0.3.2**.
19
+ Refer to the [original model card](https://huggingface.co/unsloth/gemma-3n-E2B-it) for more details on the model.
20
+ ## Use with mlx
21
+
22
+ ```bash
23
+ pip install -U mlx-vlm
24
+ ```
25
+
26
+ ```bash
27
+ python -m mlx_vlm.generate --model EZCon/gemma-3n-E2B-it-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
28
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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'] == 'audio' -%}
33
+ {{ '<audio_soft_token>' }}
34
+ {%- elif item['type'] == 'image' -%}
35
+ {{ '<image_soft_token>' }}
36
+ {%- elif item['type'] == 'text' -%}
37
+ {{ item['text'] | trim }}
38
+ {%- endif -%}
39
+ {%- endfor -%}
40
+ {%- else -%}
41
+ {{ raise_exception("Invalid content type") }}
42
+ {%- endif -%}
43
+ {{ '<end_of_turn>
44
+ ' }}
45
+ {%- endfor -%}
46
+ {%- if add_generation_prompt -%}
47
+ {{'<start_of_turn>model
48
+ '}}
49
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,430 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "Gemma3nForConditionalGeneration"
5
+ ],
6
+ "audio_config": {
7
+ "return_dict": true,
8
+ "output_hidden_states": false,
9
+ "torchscript": false,
10
+ "torch_dtype": "bfloat16",
11
+ "pruned_heads": {},
12
+ "tie_word_embeddings": true,
13
+ "chunk_size_feed_forward": 0,
14
+ "is_encoder_decoder": false,
15
+ "is_decoder": false,
16
+ "cross_attention_hidden_size": null,
17
+ "add_cross_attention": false,
18
+ "tie_encoder_decoder": false,
19
+ "architectures": null,
20
+ "finetuning_task": null,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1
28
+ },
29
+ "task_specific_params": null,
30
+ "problem_type": null,
31
+ "tokenizer_class": null,
32
+ "prefix": null,
33
+ "bos_token_id": null,
34
+ "pad_token_id": null,
35
+ "eos_token_id": null,
36
+ "sep_token_id": null,
37
+ "decoder_start_token_id": null,
38
+ "max_length": 20,
39
+ "min_length": 0,
40
+ "do_sample": false,
41
+ "early_stopping": false,
42
+ "num_beams": 1,
43
+ "num_beam_groups": 1,
44
+ "diversity_penalty": 0.0,
45
+ "temperature": 1.0,
46
+ "top_k": 50,
47
+ "top_p": 1.0,
48
+ "typical_p": 1.0,
49
+ "repetition_penalty": 1.0,
50
+ "length_penalty": 1.0,
51
+ "no_repeat_ngram_size": 0,
52
+ "encoder_no_repeat_ngram_size": 0,
53
+ "bad_words_ids": null,
54
+ "num_return_sequences": 1,
55
+ "output_scores": false,
56
+ "return_dict_in_generate": false,
57
+ "forced_bos_token_id": null,
58
+ "forced_eos_token_id": null,
59
+ "remove_invalid_values": false,
60
+ "exponential_decay_length_penalty": null,
61
+ "suppress_tokens": null,
62
+ "begin_suppress_tokens": null,
63
+ "_name_or_path": "",
64
+ "model_type": "gemma3n_audio",
65
+ "tf_legacy_loss": false,
66
+ "use_bfloat16": false,
67
+ "input_feat_size": 128,
68
+ "hidden_size": 1536,
69
+ "rms_norm_eps": 1e-06,
70
+ "vocab_size": 128,
71
+ "vocab_offset": 262272,
72
+ "gradient_clipping": 10000000000.0,
73
+ "conf_attention_chunk_size": 12,
74
+ "conf_attention_context_left": 13,
75
+ "conf_attention_context_right": 0,
76
+ "conf_attention_logit_cap": 50.0,
77
+ "conf_num_attention_heads": 8,
78
+ "conf_num_hidden_layers": 12,
79
+ "conf_conv_kernel_size": 5,
80
+ "conf_reduction_factor": 4,
81
+ "conf_residual_weight": 0.5,
82
+ "sscp_conv_channel_size": [
83
+ 128,
84
+ 32
85
+ ],
86
+ "sscp_conv_group_norm_eps": 0.001,
87
+ "sscp_conv_kernel_size": [
88
+ [
89
+ 3,
90
+ 3
91
+ ],
92
+ [
93
+ 3,
94
+ 3
95
+ ]
96
+ ],
97
+ "sscp_conv_stride_size": [
98
+ [
99
+ 2,
100
+ 2
101
+ ],
102
+ [
103
+ 2,
104
+ 2
105
+ ]
106
+ ],
107
+ "output_attentions": false
108
+ },
109
+ "audio_soft_tokens_per_image": 188,
110
+ "audio_token_id": 262273,
111
+ "bad_words_ids": null,
112
+ "begin_suppress_tokens": null,
113
+ "boa_token_id": 256000,
114
+ "boi_token_id": 255999,
115
+ "bos_token_id": 2,
116
+ "chunk_size_feed_forward": 0,
117
+ "cross_attention_hidden_size": null,
118
+ "decoder_start_token_id": null,
119
+ "diversity_penalty": 0.0,
120
+ "do_sample": false,
121
+ "early_stopping": false,
122
+ "encoder_no_repeat_ngram_size": 0,
123
+ "eoa_token_id": 262272,
124
+ "eoi_token_id": 262144,
125
+ "eos_token_id": 106,
126
+ "exponential_decay_length_penalty": null,
127
+ "finetuning_task": null,
128
+ "forced_bos_token_id": null,
129
+ "forced_eos_token_id": null,
130
+ "id2label": {
131
+ "0": "LABEL_0",
132
+ "1": "LABEL_1"
133
+ },
134
+ "image_token_id": 262145,
135
+ "initializer_range": 0.02,
136
+ "is_decoder": false,
137
+ "is_encoder_decoder": false,
138
+ "label2id": {
139
+ "LABEL_0": 0,
140
+ "LABEL_1": 1
141
+ },
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "min_length": 0,
145
+ "model_type": "gemma3n",
146
+ "no_repeat_ngram_size": 0,
147
+ "num_beam_groups": 1,
148
+ "num_beams": 1,
149
+ "num_return_sequences": 1,
150
+ "output_attentions": false,
151
+ "output_hidden_states": false,
152
+ "output_scores": false,
153
+ "pad_token_id": 0,
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "pruned_heads": {},
157
+ "remove_invalid_values": false,
158
+ "repetition_penalty": 1.0,
159
+ "return_dict": true,
160
+ "return_dict_in_generate": false,
161
+ "sep_token_id": null,
162
+ "suppress_tokens": null,
163
+ "task_specific_params": null,
164
+ "temperature": 1.0,
165
+ "text_config": {
166
+ "return_dict": true,
167
+ "output_hidden_states": false,
168
+ "torchscript": false,
169
+ "torch_dtype": "bfloat16",
170
+ "pruned_heads": {},
171
+ "tie_word_embeddings": true,
172
+ "chunk_size_feed_forward": 0,
173
+ "is_encoder_decoder": false,
174
+ "is_decoder": false,
175
+ "cross_attention_hidden_size": null,
176
+ "add_cross_attention": false,
177
+ "tie_encoder_decoder": false,
178
+ "architectures": null,
179
+ "finetuning_task": null,
180
+ "id2label": {
181
+ "0": "LABEL_0",
182
+ "1": "LABEL_1"
183
+ },
184
+ "label2id": {
185
+ "LABEL_0": 0,
186
+ "LABEL_1": 1
187
+ },
188
+ "task_specific_params": null,
189
+ "problem_type": null,
190
+ "tokenizer_class": null,
191
+ "prefix": null,
192
+ "bos_token_id": 2,
193
+ "pad_token_id": 0,
194
+ "eos_token_id": 1,
195
+ "sep_token_id": null,
196
+ "decoder_start_token_id": null,
197
+ "max_length": 20,
198
+ "min_length": 0,
199
+ "do_sample": false,
200
+ "early_stopping": false,
201
+ "num_beams": 1,
202
+ "num_beam_groups": 1,
203
+ "diversity_penalty": 0.0,
204
+ "temperature": 1.0,
205
+ "top_k": 50,
206
+ "top_p": 1.0,
207
+ "typical_p": 1.0,
208
+ "repetition_penalty": 1.0,
209
+ "length_penalty": 1.0,
210
+ "no_repeat_ngram_size": 0,
211
+ "encoder_no_repeat_ngram_size": 0,
212
+ "bad_words_ids": null,
213
+ "num_return_sequences": 1,
214
+ "output_scores": false,
215
+ "return_dict_in_generate": false,
216
+ "forced_bos_token_id": null,
217
+ "forced_eos_token_id": null,
218
+ "remove_invalid_values": false,
219
+ "exponential_decay_length_penalty": null,
220
+ "suppress_tokens": null,
221
+ "begin_suppress_tokens": null,
222
+ "_name_or_path": "",
223
+ "model_type": "gemma3n_text",
224
+ "tf_legacy_loss": false,
225
+ "use_bfloat16": false,
226
+ "vocab_size": 262400,
227
+ "vocab_size_per_layer_input": 262144,
228
+ "max_position_embeddings": 32768,
229
+ "hidden_size": 2048,
230
+ "intermediate_size": [
231
+ 8192,
232
+ 8192,
233
+ 8192,
234
+ 8192,
235
+ 8192,
236
+ 8192,
237
+ 8192,
238
+ 8192,
239
+ 8192,
240
+ 8192,
241
+ 8192,
242
+ 8192,
243
+ 8192,
244
+ 8192,
245
+ 8192,
246
+ 8192,
247
+ 8192,
248
+ 8192,
249
+ 8192,
250
+ 8192,
251
+ 8192,
252
+ 8192,
253
+ 8192,
254
+ 8192,
255
+ 8192,
256
+ 8192,
257
+ 8192,
258
+ 8192,
259
+ 8192,
260
+ 8192
261
+ ],
262
+ "num_hidden_layers": 30,
263
+ "num_attention_heads": 8,
264
+ "head_dim": 256,
265
+ "num_key_value_heads": 2,
266
+ "initializer_range": 0.02,
267
+ "rms_norm_eps": 1e-06,
268
+ "use_cache": true,
269
+ "rope_theta": 1000000.0,
270
+ "attention_bias": false,
271
+ "attention_dropout": 0.0,
272
+ "hidden_activation": "gelu_pytorch_tanh",
273
+ "sliding_window": 512,
274
+ "final_logit_softcapping": 30.0,
275
+ "layer_types": [
276
+ "sliding_attention",
277
+ "sliding_attention",
278
+ "sliding_attention",
279
+ "sliding_attention",
280
+ "full_attention",
281
+ "sliding_attention",
282
+ "sliding_attention",
283
+ "sliding_attention",
284
+ "sliding_attention",
285
+ "full_attention",
286
+ "sliding_attention",
287
+ "sliding_attention",
288
+ "sliding_attention",
289
+ "sliding_attention",
290
+ "full_attention",
291
+ "sliding_attention",
292
+ "sliding_attention",
293
+ "sliding_attention",
294
+ "sliding_attention",
295
+ "full_attention",
296
+ "sliding_attention",
297
+ "sliding_attention",
298
+ "sliding_attention",
299
+ "sliding_attention",
300
+ "full_attention",
301
+ "sliding_attention",
302
+ "sliding_attention",
303
+ "sliding_attention",
304
+ "sliding_attention",
305
+ "full_attention"
306
+ ],
307
+ "rope_local_base_freq": 10000.0,
308
+ "rope_scaling": null,
309
+ "hidden_size_per_layer_input": 256,
310
+ "num_kv_shared_layers": 10,
311
+ "altup_active_idx": 0,
312
+ "altup_coef_clip": 120.0,
313
+ "altup_correct_scale": true,
314
+ "altup_num_inputs": 4,
315
+ "laurel_rank": 64,
316
+ "activation_sparsity_pattern": [
317
+ 0.95,
318
+ 0.95,
319
+ 0.95,
320
+ 0.95,
321
+ 0.95,
322
+ 0.95,
323
+ 0.95,
324
+ 0.95,
325
+ 0.95,
326
+ 0.95,
327
+ 0.0,
328
+ 0.0,
329
+ 0.0,
330
+ 0.0,
331
+ 0.0,
332
+ 0.0,
333
+ 0.0,
334
+ 0.0,
335
+ 0.0,
336
+ 0.0,
337
+ 0.0,
338
+ 0.0,
339
+ 0.0,
340
+ 0.0,
341
+ 0.0,
342
+ 0.0,
343
+ 0.0,
344
+ 0.0,
345
+ 0.0,
346
+ 0.0
347
+ ],
348
+ "output_attentions": false
349
+ },
350
+ "tf_legacy_loss": false,
351
+ "tie_encoder_decoder": false,
352
+ "tie_word_embeddings": true,
353
+ "tokenizer_class": null,
354
+ "top_k": 50,
355
+ "top_p": 1.0,
356
+ "torchscript": false,
357
+ "transformers_version": "4.55.0.dev0",
358
+ "typical_p": 1.0,
359
+ "unsloth_fixed": true,
360
+ "use_bfloat16": false,
361
+ "vision_config": {
362
+ "return_dict": true,
363
+ "output_hidden_states": false,
364
+ "torchscript": false,
365
+ "torch_dtype": "bfloat16",
366
+ "pruned_heads": {},
367
+ "tie_word_embeddings": true,
368
+ "chunk_size_feed_forward": 0,
369
+ "is_encoder_decoder": false,
370
+ "is_decoder": false,
371
+ "cross_attention_hidden_size": null,
372
+ "add_cross_attention": false,
373
+ "tie_encoder_decoder": false,
374
+ "architectures": null,
375
+ "finetuning_task": null,
376
+ "task_specific_params": null,
377
+ "problem_type": null,
378
+ "tokenizer_class": null,
379
+ "prefix": null,
380
+ "bos_token_id": null,
381
+ "pad_token_id": null,
382
+ "eos_token_id": null,
383
+ "sep_token_id": null,
384
+ "decoder_start_token_id": null,
385
+ "max_length": 20,
386
+ "min_length": 0,
387
+ "do_sample": false,
388
+ "early_stopping": false,
389
+ "num_beams": 1,
390
+ "num_beam_groups": 1,
391
+ "diversity_penalty": 0.0,
392
+ "temperature": 1.0,
393
+ "top_k": 50,
394
+ "top_p": 1.0,
395
+ "typical_p": 1.0,
396
+ "repetition_penalty": 1.0,
397
+ "length_penalty": 1.0,
398
+ "no_repeat_ngram_size": 0,
399
+ "encoder_no_repeat_ngram_size": 0,
400
+ "bad_words_ids": null,
401
+ "num_return_sequences": 1,
402
+ "output_scores": false,
403
+ "return_dict_in_generate": false,
404
+ "forced_bos_token_id": null,
405
+ "forced_eos_token_id": null,
406
+ "remove_invalid_values": false,
407
+ "exponential_decay_length_penalty": null,
408
+ "suppress_tokens": null,
409
+ "begin_suppress_tokens": null,
410
+ "_name_or_path": "",
411
+ "label_names": [
412
+ "LABEL_0",
413
+ "LABEL_1"
414
+ ],
415
+ "model_type": "gemma3n_vision",
416
+ "num_classes": 2,
417
+ "tf_legacy_loss": false,
418
+ "use_bfloat16": false,
419
+ "initializer_range": 0.02,
420
+ "do_pooling": false,
421
+ "model_args": null,
422
+ "architecture": "mobilenetv5_300m_enc",
423
+ "hidden_size": 2048,
424
+ "vocab_size": 128,
425
+ "vocab_offset": 262144,
426
+ "rms_norm_eps": 1e-06,
427
+ "output_attentions": false
428
+ },
429
+ "vision_soft_tokens_per_image": 256
430
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.53.1"
13
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8708d213b8c018f0d912495f220e8f7008a570767e1d461c0284831c719a46
3
+ size 4804083035
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871259b8267516ce45f4a54016b86e0abc5716b85c96e7250daa4431606f1326
3
+ size 5350795457
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c611e6b1976f25da23196d897eb68f9d6fd865e7bb8101f4f5d92b556e25e815
3
+ size 724201340
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": false,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "dither": 0.0,
8
+ "do_center_crop": null,
9
+ "do_convert_rgb": null,
10
+ "do_normalize": false,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "feature_size": 128,
14
+ "fft_length": 1024,
15
+ "fft_overdrive": true,
16
+ "frame_length": 512,
17
+ "hop_length": 160,
18
+ "image_mean": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "image_processor_type": "SiglipImageProcessorFast",
24
+ "image_seq_length": 256,
25
+ "image_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "input_data_format": null,
31
+ "input_scale_factor": 1.0,
32
+ "max_frequency": 7600.0,
33
+ "mel_floor": 1e-05,
34
+ "min_frequency": 125.0,
35
+ "padding_side": "left",
36
+ "padding_value": 0.0,
37
+ "per_bin_mean": null,
38
+ "per_bin_stddev": null,
39
+ "preemphasis": 0.97,
40
+ "preemphasis_htk_flavor": true,
41
+ "processor_class": "Gemma3nProcessor",
42
+ "resample": 2,
43
+ "rescale_factor": 0.00392156862745098,
44
+ "return_attention_mask": true,
45
+ "return_tensors": null,
46
+ "sampling_rate": 16000,
47
+ "size": {
48
+ "height": 768,
49
+ "width": 768
50
+ }
51
+ }
processor_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "audio_seq_length": 188,
3
+ "image_seq_length": 256,
4
+ "processor_class": "Gemma3nProcessor"
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_token": "<audio_soft_token>",
3
+ "boa_token": "<start_of_audio>",
4
+ "boi_token": "<start_of_image>",
5
+ "bos_token": {
6
+ "content": "<bos>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eoa_token": "<end_of_audio>",
13
+ "eoi_token": "<end_of_image>",
14
+ "eos_token": {
15
+ "content": "<end_of_turn>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "image_token": "<image_soft_token>",
22
+ "pad_token": {
23
+ "content": "<pad>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
3
+ size 33442553
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff