Hugging Face's logo

Puujeeeeeeeeeeee
/
cpt-round3

Image-Text-to-Text
Transformers
Safetensors
English
gemma4
text-generation-inference
unsloth
Model card Files
xet
 Community
Puujeeeeeeeeeeee commited on
Commit
3599850
·
verified ·
1 Parent(s): 94dda5f

(Trained with Unsloth)

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. config.json +200 -0
  3. generation_config.json +12 -0
  4. processor_config.json +75 -0
  5. tokenizer.json +3 -0
  6. tokenizer_config.json +253 -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
config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token_id": 2,
49
+ "torch_dtype": "bfloat16",
50
+ "eoa_token_id": 258883,
51
+ "eoa_token_index": 258883,
52
+ "eoi_token_id": 258882,
53
+ "eos_token_id": 1,
54
+ "image_token_id": 258880,
55
+ "initializer_range": 0.02,
56
+ "model_name": "Puujeeeeeeeeeeee/cpt-round2",
57
+ "model_type": "gemma4",
58
+ "pad_token_id": 0,
59
+ "text_config": {
60
+ "attention_bias": false,
61
+ "attention_dropout": 0.0,
62
+ "attention_k_eq_v": false,
63
+ "bos_token_id": 2,
64
+ "torch_dtype": "bfloat16",
65
+ "enable_moe_block": false,
66
+ "eos_token_id": 1,
67
+ "expert_intermediate_size": null,
68
+ "final_logit_softcapping": 30.0,
69
+ "global_head_dim": 512,
70
+ "head_dim": 256,
71
+ "hidden_activation": "gelu_pytorch_tanh",
72
+ "hidden_size": 2560,
73
+ "hidden_size_per_layer_input": 256,
74
+ "initializer_range": 0.02,
75
+ "intermediate_size": 10240,
76
+ "layer_types": [
77
+ "sliding_attention",
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
+ "sliding_attention",
88
+ "full_attention",
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "full_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "full_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "full_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "full_attention",
113
+ "sliding_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "sliding_attention",
117
+ "sliding_attention",
118
+ "full_attention"
119
+ ],
120
+ "max_position_embeddings": 131072,
121
+ "model_type": "gemma4_text",
122
+ "moe_intermediate_size": null,
123
+ "num_attention_heads": 8,
124
+ "num_experts": null,
125
+ "num_global_key_value_heads": null,
126
+ "num_hidden_layers": 42,
127
+ "num_key_value_heads": 2,
128
+ "num_kv_shared_layers": 18,
129
+ "pad_token_id": 0,
130
+ "rms_norm_eps": 1e-06,
131
+ "rope_parameters": {
132
+ "full_attention": {
133
+ "partial_rotary_factor": 0.25,
134
+ "rope_theta": 1000000.0,
135
+ "rope_type": "proportional"
136
+ },
137
+ "sliding_attention": {
138
+ "rope_theta": 10000.0,
139
+ "rope_type": "default"
140
+ }
141
+ },
142
+ "sliding_window": 512,
143
+ "tie_word_embeddings": true,
144
+ "top_k_experts": null,
145
+ "use_bidirectional_attention": null,
146
+ "use_cache": false,
147
+ "use_double_wide_mlp": false,
148
+ "vocab_size": 262144,
149
+ "vocab_size_per_layer_input": 262144
150
+ },
151
+ "tie_word_embeddings": true,
152
+ "unsloth_fixed": true,
153
+ "unsloth_version": "2026.6.9",
154
+ "use_cache": false,
155
+ "video_token_id": 258884,
156
+ "vision_config": {
157
+ "_name_or_path": "",
158
+ "architectures": null,
159
+ "attention_bias": false,
160
+ "attention_dropout": 0.0,
161
+ "chunk_size_feed_forward": 0,
162
+ "default_output_length": 280,
163
+ "torch_dtype": "bfloat16",
164
+ "global_head_dim": 64,
165
+ "head_dim": 64,
166
+ "hidden_activation": "gelu_pytorch_tanh",
167
+ "hidden_size": 768,
168
+ "id2label": {
169
+ "0": "LABEL_0",
170
+ "1": "LABEL_1"
171
+ },
172
+ "initializer_range": 0.02,
173
+ "intermediate_size": 3072,
174
+ "is_encoder_decoder": false,
175
+ "label2id": {
176
+ "LABEL_0": 0,
177
+ "LABEL_1": 1
178
+ },
179
+ "max_position_embeddings": 131072,
180
+ "model_type": "gemma4_vision",
181
+ "num_attention_heads": 12,
182
+ "num_hidden_layers": 16,
183
+ "num_key_value_heads": 12,
184
+ "output_attentions": false,
185
+ "output_hidden_states": false,
186
+ "patch_size": 16,
187
+ "pooling_kernel_size": 3,
188
+ "position_embedding_size": 10240,
189
+ "problem_type": null,
190
+ "return_dict": true,
191
+ "rms_norm_eps": 1e-06,
192
+ "rope_parameters": {
193
+ "rope_theta": 100.0,
194
+ "rope_type": "default"
195
+ },
196
+ "standardize": false,
197
+ "use_clipped_linears": true
198
+ },
199
+ "vision_soft_tokens_per_image": 280
200
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "temperature": 1.0,
9
+ "top_k": 64,
10
+ "top_p": 0.95,
11
+ "transformers_version": "5.13.0"
12
+ }
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:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
3
+ size 32169626
tokenizer_config.json ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "local_files_only": false,
22
+ "mask_token": "<mask>",
23
+ "max_length": 1024,
24
+ "model_max_length": 131072,
25
+ "model_specific_special_tokens": {
26
+ "audio_token": "<|audio|>",
27
+ "boa_token": "<|audio>",
28
+ "boi_token": "<|image>",
29
+ "eoa_token": "<audio|>",
30
+ "eoc_token": "<channel|>",
31
+ "eoi_token": "<image|>",
32
+ "eot_token": "<turn|>",
33
+ "escape_token": "<|\"|>",
34
+ "etc_token": "<tool_call|>",
35
+ "etd_token": "<tool|>",
36
+ "etr_token": "<tool_response|>",
37
+ "image_token": "<|image|>",
38
+ "soc_token": "<|channel>",
39
+ "sot_token": "<|turn>",
40
+ "stc_token": "<|tool_call>",
41
+ "std_token": "<|tool>",
42
+ "str_token": "<|tool_response>",
43
+ "think_token": "<|think|>"
44
+ },
45
+ "pad_token": "<pad>",
46
+ "padding_side": "right",
47
+ "processor_class": "Gemma4Processor",
48
+ "soc_token": "<|channel>",
49
+ "sot_token": "<|turn>",
50
+ "stc_token": "<|tool_call>",
51
+ "std_token": "<|tool>",
52
+ "str_token": "<|tool_response>",
53
+ "stride": 0,
54
+ "think_token": "<|think|>",
55
+ "tokenizer_class": "GemmaTokenizer",
56
+ "truncation_side": "right",
57
+ "truncation_strategy": "longest_first",
58
+ "unk_token": "<unk>",
59
+ "added_tokens_decoder": {
60
+ "0": {
61
+ "content": "<pad>",
62
+ "single_word": false,
63
+ "lstrip": false,
64
+ "rstrip": false,
65
+ "normalized": false,
66
+ "special": true
67
+ },
68
+ "1": {
69
+ "content": "<eos>",
70
+ "single_word": false,
71
+ "lstrip": false,
72
+ "rstrip": false,
73
+ "normalized": false,
74
+ "special": true
75
+ },
76
+ "2": {
77
+ "content": "<bos>",
78
+ "single_word": false,
79
+ "lstrip": false,
80
+ "rstrip": false,
81
+ "normalized": false,
82
+ "special": true
83
+ },
84
+ "3": {
85
+ "content": "<unk>",
86
+ "single_word": false,
87
+ "lstrip": false,
88
+ "rstrip": false,
89
+ "normalized": false,
90
+ "special": true
91
+ },
92
+ "4": {
93
+ "content": "<mask>",
94
+ "single_word": false,
95
+ "lstrip": false,
96
+ "rstrip": false,
97
+ "normalized": false,
98
+ "special": true
99
+ },
100
+ "46": {
101
+ "content": "<|tool>",
102
+ "single_word": false,
103
+ "lstrip": false,
104
+ "rstrip": false,
105
+ "normalized": false,
106
+ "special": true
107
+ },
108
+ "47": {
109
+ "content": "<tool|>",
110
+ "single_word": false,
111
+ "lstrip": false,
112
+ "rstrip": false,
113
+ "normalized": false,
114
+ "special": true
115
+ },
116
+ "48": {
117
+ "content": "<|tool_call>",
118
+ "single_word": false,
119
+ "lstrip": false,
120
+ "rstrip": false,
121
+ "normalized": false,
122
+ "special": true
123
+ },
124
+ "49": {
125
+ "content": "<tool_call|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ "50": {
133
+ "content": "<|tool_response>",
134
+ "single_word": false,
135
+ "lstrip": false,
136
+ "rstrip": false,
137
+ "normalized": false,
138
+ "special": true
139
+ },
140
+ "51": {
141
+ "content": "<tool_response|>",
142
+ "single_word": false,
143
+ "lstrip": false,
144
+ "rstrip": false,
145
+ "normalized": false,
146
+ "special": true
147
+ },
148
+ "52": {
149
+ "content": "<|\"|>",
150
+ "single_word": false,
151
+ "lstrip": false,
152
+ "rstrip": false,
153
+ "normalized": false,
154
+ "special": true
155
+ },
156
+ "98": {
157
+ "content": "<|think|>",
158
+ "single_word": false,
159
+ "lstrip": false,
160
+ "rstrip": false,
161
+ "normalized": false,
162
+ "special": true
163
+ },
164
+ "100": {
165
+ "content": "<|channel>",
166
+ "single_word": false,
167
+ "lstrip": false,
168
+ "rstrip": false,
169
+ "normalized": false,
170
+ "special": true
171
+ },
172
+ "101": {
173
+ "content": "<channel|>",
174
+ "single_word": false,
175
+ "lstrip": false,
176
+ "rstrip": false,
177
+ "normalized": false,
178
+ "special": true
179
+ },
180
+ "105": {
181
+ "content": "<|turn>",
182
+ "single_word": false,
183
+ "lstrip": false,
184
+ "rstrip": false,
185
+ "normalized": false,
186
+ "special": true
187
+ },
188
+ "106": {
189
+ "content": "<turn|>",
190
+ "single_word": false,
191
+ "lstrip": false,
192
+ "rstrip": false,
193
+ "normalized": false,
194
+ "special": true
195
+ },
196
+ "255999": {
197
+ "content": "<|image>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ "256000": {
205
+ "content": "<|audio>",
206
+ "single_word": false,
207
+ "lstrip": false,
208
+ "rstrip": false,
209
+ "normalized": false,
210
+ "special": true
211
+ },
212
+ "258880": {
213
+ "content": "<|image|>",
214
+ "single_word": false,
215
+ "lstrip": false,
216
+ "rstrip": false,
217
+ "normalized": false,
218
+ "special": true
219
+ },
220
+ "258881": {
221
+ "content": "<|audio|>",
222
+ "single_word": false,
223
+ "lstrip": false,
224
+ "rstrip": false,
225
+ "normalized": false,
226
+ "special": true
227
+ },
228
+ "258882": {
229
+ "content": "<image|>",
230
+ "single_word": false,
231
+ "lstrip": false,
232
+ "rstrip": false,
233
+ "normalized": false,
234
+ "special": true
235
+ },
236
+ "258883": {
237
+ "content": "<audio|>",
238
+ "single_word": false,
239
+ "lstrip": false,
240
+ "rstrip": false,
241
+ "normalized": false,
242
+ "special": true
243
+ },
244
+ "258884": {
245
+ "content": "<|video|>",
246
+ "single_word": false,
247
+ "lstrip": false,
248
+ "rstrip": false,
249
+ "normalized": false,
250
+ "special": true
251
+ }
252
+ }
253
+ }