ovinduG commited on
Commit
b683fa4
·
verified ·
1 Parent(s): e01f2b1

(Trained with Unsloth)

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
config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_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
+ "torch_dtype": "bfloat16",
49
+ "eoa_token_id": 258883,
50
+ "eoa_token_index": 258883,
51
+ "eoi_token_id": 258882,
52
+ "image_token_id": 258880,
53
+ "initializer_range": 0.02,
54
+ "model_type": "gemma4",
55
+ "text_config": {
56
+ "attention_bias": false,
57
+ "attention_dropout": 0.0,
58
+ "attention_k_eq_v": false,
59
+ "bos_token_id": 2,
60
+ "torch_dtype": "bfloat16",
61
+ "enable_moe_block": false,
62
+ "eos_token_id": 1,
63
+ "expert_intermediate_size": null,
64
+ "final_logit_softcapping": 30.0,
65
+ "global_head_dim": 512,
66
+ "head_dim": 256,
67
+ "hidden_activation": "gelu_pytorch_tanh",
68
+ "hidden_size": 2560,
69
+ "hidden_size_per_layer_input": 256,
70
+ "initializer_range": 0.02,
71
+ "intermediate_size": 10240,
72
+ "layer_types": [
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
+ "sliding_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
+ "sliding_attention",
108
+ "full_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "sliding_attention",
113
+ "sliding_attention",
114
+ "full_attention"
115
+ ],
116
+ "max_position_embeddings": 131072,
117
+ "model_type": "gemma4_text",
118
+ "moe_intermediate_size": null,
119
+ "num_attention_heads": 8,
120
+ "num_experts": null,
121
+ "num_global_key_value_heads": null,
122
+ "num_hidden_layers": 42,
123
+ "num_key_value_heads": 2,
124
+ "num_kv_shared_layers": 18,
125
+ "pad_token_id": 0,
126
+ "rms_norm_eps": 1e-06,
127
+ "rope_parameters": {
128
+ "full_attention": {
129
+ "partial_rotary_factor": 0.25,
130
+ "rope_theta": 1000000.0,
131
+ "rope_type": "proportional"
132
+ },
133
+ "sliding_attention": {
134
+ "rope_theta": 10000.0,
135
+ "rope_type": "default"
136
+ }
137
+ },
138
+ "sliding_window": 512,
139
+ "tie_word_embeddings": true,
140
+ "top_k_experts": null,
141
+ "use_bidirectional_attention": null,
142
+ "use_cache": true,
143
+ "use_double_wide_mlp": false,
144
+ "vocab_size": 262144,
145
+ "vocab_size_per_layer_input": 262144
146
+ },
147
+ "tie_word_embeddings": true,
148
+ "transformers_version": "5.5.0",
149
+ "video_token_id": 258884,
150
+ "vision_config": {
151
+ "_name_or_path": "",
152
+ "architectures": null,
153
+ "attention_bias": false,
154
+ "attention_dropout": 0.0,
155
+ "chunk_size_feed_forward": 0,
156
+ "default_output_length": 280,
157
+ "torch_dtype": "bfloat16",
158
+ "global_head_dim": 64,
159
+ "head_dim": 64,
160
+ "hidden_activation": "gelu_pytorch_tanh",
161
+ "hidden_size": 768,
162
+ "id2label": {
163
+ "0": "LABEL_0",
164
+ "1": "LABEL_1"
165
+ },
166
+ "initializer_range": 0.02,
167
+ "intermediate_size": 3072,
168
+ "is_encoder_decoder": false,
169
+ "label2id": {
170
+ "LABEL_0": 0,
171
+ "LABEL_1": 1
172
+ },
173
+ "max_position_embeddings": 131072,
174
+ "model_type": "gemma4_vision",
175
+ "num_attention_heads": 12,
176
+ "num_hidden_layers": 16,
177
+ "num_key_value_heads": 12,
178
+ "output_attentions": false,
179
+ "output_hidden_states": false,
180
+ "patch_size": 16,
181
+ "pooling_kernel_size": 3,
182
+ "position_embedding_size": 10240,
183
+ "problem_type": null,
184
+ "return_dict": true,
185
+ "rms_norm_eps": 1e-06,
186
+ "rope_parameters": {
187
+ "rope_theta": 100.0,
188
+ "rope_type": "default"
189
+ },
190
+ "standardize": false,
191
+ "use_clipped_linears": true
192
+ },
193
+ "vision_soft_tokens_per_image": 280
194
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "do_sample": true,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "temperature": 1.0,
7
+ "top_k": 64,
8
+ "top_p": 0.95,
9
+ "transformers_version": "5.5.0"
10
+ }
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 sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
3
+ size 32170070
tokenizer_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
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
+ "soc_token": "<|channel>",
47
+ "sot_token": "<|turn>",
48
+ "stc_token": "<|tool_call>",
49
+ "std_token": "<|tool>",
50
+ "str_token": "<|tool_response>",
51
+ "think_token": "<|think|>",
52
+ "tokenizer_class": "GemmaTokenizer",
53
+ "unk_token": "<unk>",
54
+ "added_tokens_decoder": {
55
+ "0": {
56
+ "content": "<pad>",
57
+ "single_word": false,
58
+ "lstrip": false,
59
+ "rstrip": false,
60
+ "normalized": false,
61
+ "special": true
62
+ },
63
+ "1": {
64
+ "content": "<eos>",
65
+ "single_word": false,
66
+ "lstrip": false,
67
+ "rstrip": false,
68
+ "normalized": false,
69
+ "special": true
70
+ },
71
+ "2": {
72
+ "content": "<bos>",
73
+ "single_word": false,
74
+ "lstrip": false,
75
+ "rstrip": false,
76
+ "normalized": false,
77
+ "special": true
78
+ },
79
+ "3": {
80
+ "content": "<unk>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ "4": {
88
+ "content": "<mask>",
89
+ "single_word": false,
90
+ "lstrip": false,
91
+ "rstrip": false,
92
+ "normalized": false,
93
+ "special": true
94
+ },
95
+ "46": {
96
+ "content": "<|tool>",
97
+ "single_word": false,
98
+ "lstrip": false,
99
+ "rstrip": false,
100
+ "normalized": false,
101
+ "special": true
102
+ },
103
+ "47": {
104
+ "content": "<tool|>",
105
+ "single_word": false,
106
+ "lstrip": false,
107
+ "rstrip": false,
108
+ "normalized": false,
109
+ "special": true
110
+ },
111
+ "48": {
112
+ "content": "<|tool_call>",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": false,
117
+ "special": true
118
+ },
119
+ "49": {
120
+ "content": "<tool_call|>",
121
+ "single_word": false,
122
+ "lstrip": false,
123
+ "rstrip": false,
124
+ "normalized": false,
125
+ "special": true
126
+ },
127
+ "50": {
128
+ "content": "<|tool_response>",
129
+ "single_word": false,
130
+ "lstrip": false,
131
+ "rstrip": false,
132
+ "normalized": false,
133
+ "special": true
134
+ },
135
+ "51": {
136
+ "content": "<tool_response|>",
137
+ "single_word": false,
138
+ "lstrip": false,
139
+ "rstrip": false,
140
+ "normalized": false,
141
+ "special": true
142
+ },
143
+ "52": {
144
+ "content": "<|\"|>",
145
+ "single_word": false,
146
+ "lstrip": false,
147
+ "rstrip": false,
148
+ "normalized": false,
149
+ "special": true
150
+ },
151
+ "98": {
152
+ "content": "<|think|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ "100": {
160
+ "content": "<|channel>",
161
+ "single_word": false,
162
+ "lstrip": false,
163
+ "rstrip": false,
164
+ "normalized": false,
165
+ "special": true
166
+ },
167
+ "101": {
168
+ "content": "<channel|>",
169
+ "single_word": false,
170
+ "lstrip": false,
171
+ "rstrip": false,
172
+ "normalized": false,
173
+ "special": true
174
+ },
175
+ "105": {
176
+ "content": "<|turn>",
177
+ "single_word": false,
178
+ "lstrip": false,
179
+ "rstrip": false,
180
+ "normalized": false,
181
+ "special": true
182
+ },
183
+ "106": {
184
+ "content": "<turn|>",
185
+ "single_word": false,
186
+ "lstrip": false,
187
+ "rstrip": false,
188
+ "normalized": false,
189
+ "special": true
190
+ },
191
+ "255999": {
192
+ "content": "<|image>",
193
+ "single_word": false,
194
+ "lstrip": false,
195
+ "rstrip": false,
196
+ "normalized": false,
197
+ "special": true
198
+ },
199
+ "256000": {
200
+ "content": "<|audio>",
201
+ "single_word": false,
202
+ "lstrip": false,
203
+ "rstrip": false,
204
+ "normalized": false,
205
+ "special": true
206
+ },
207
+ "258880": {
208
+ "content": "<|image|>",
209
+ "single_word": false,
210
+ "lstrip": false,
211
+ "rstrip": false,
212
+ "normalized": false,
213
+ "special": true
214
+ },
215
+ "258881": {
216
+ "content": "<|audio|>",
217
+ "single_word": false,
218
+ "lstrip": false,
219
+ "rstrip": false,
220
+ "normalized": false,
221
+ "special": true
222
+ },
223
+ "258882": {
224
+ "content": "<image|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ "258883": {
232
+ "content": "<audio|>",
233
+ "single_word": false,
234
+ "lstrip": false,
235
+ "rstrip": false,
236
+ "normalized": false,
237
+ "special": true
238
+ },
239
+ "258884": {
240
+ "content": "<|video|>",
241
+ "single_word": false,
242
+ "lstrip": false,
243
+ "rstrip": false,
244
+ "normalized": false,
245
+ "special": true
246
+ }
247
+ }
248
+ }