Hugging Face's logo

Puujeeeeeeeeeeee
/
cpt-round1

Image-Text-to-Text
Transformers
Safetensors
English
gemma4
text-generation-inference
unsloth
Model card Files
xet
 Community
Puujeeeeeeeeeeee commited on
Commit
67030df
·
verified ·
1 Parent(s): 04e7224

(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 +249 -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": "unsloth/gemma-4-e4b-unsloth-bnb-4bit",
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 sha256:55e53b7789842253453fe481c7b5c4ce98cd61654cb333bb39a78e9ed824871d
3
+ size 32169725
tokenizer_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 131072,
24
+ "model_specific_special_tokens": {
25
+ "audio_token": "<|audio|>",
26
+ "boa_token": "<|audio>",
27
+ "boi_token": "<|image>",
28
+ "eoa_token": "<audio|>",
29
+ "eoc_token": "<channel|>",
30
+ "eoi_token": "<image|>",
31
+ "eot_token": "<turn|>",
32
+ "escape_token": "<|\"|>",
33
+ "etc_token": "<tool_call|>",
34
+ "etd_token": "<tool|>",
35
+ "etr_token": "<tool_response|>",
36
+ "image_token": "<|image|>",
37
+ "soc_token": "<|channel>",
38
+ "sot_token": "<|turn>",
39
+ "stc_token": "<|tool_call>",
40
+ "std_token": "<|tool>",
41
+ "str_token": "<|tool_response>",
42
+ "think_token": "<|think|>"
43
+ },
44
+ "pad_token": "<pad>",
45
+ "padding_side": "right",
46
+ "processor_class": "Gemma4Processor",
47
+ "soc_token": "<|channel>",
48
+ "sot_token": "<|turn>",
49
+ "stc_token": "<|tool_call>",
50
+ "std_token": "<|tool>",
51
+ "str_token": "<|tool_response>",
52
+ "think_token": "<|think|>",
53
+ "tokenizer_class": "GemmaTokenizer",
54
+ "unk_token": "<unk>",
55
+ "added_tokens_decoder": {
56
+ "0": {
57
+ "content": "<pad>",
58
+ "single_word": false,
59
+ "lstrip": false,
60
+ "rstrip": false,
61
+ "normalized": false,
62
+ "special": true
63
+ },
64
+ "1": {
65
+ "content": "<eos>",
66
+ "single_word": false,
67
+ "lstrip": false,
68
+ "rstrip": false,
69
+ "normalized": false,
70
+ "special": true
71
+ },
72
+ "2": {
73
+ "content": "<bos>",
74
+ "single_word": false,
75
+ "lstrip": false,
76
+ "rstrip": false,
77
+ "normalized": false,
78
+ "special": true
79
+ },
80
+ "3": {
81
+ "content": "<unk>",
82
+ "single_word": false,
83
+ "lstrip": false,
84
+ "rstrip": false,
85
+ "normalized": false,
86
+ "special": true
87
+ },
88
+ "4": {
89
+ "content": "<mask>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ "46": {
97
+ "content": "<|tool>",
98
+ "single_word": false,
99
+ "lstrip": false,
100
+ "rstrip": false,
101
+ "normalized": false,
102
+ "special": true
103
+ },
104
+ "47": {
105
+ "content": "<tool|>",
106
+ "single_word": false,
107
+ "lstrip": false,
108
+ "rstrip": false,
109
+ "normalized": false,
110
+ "special": true
111
+ },
112
+ "48": {
113
+ "content": "<|tool_call>",
114
+ "single_word": false,
115
+ "lstrip": false,
116
+ "rstrip": false,
117
+ "normalized": false,
118
+ "special": true
119
+ },
120
+ "49": {
121
+ "content": "<tool_call|>",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": false,
126
+ "special": true
127
+ },
128
+ "50": {
129
+ "content": "<|tool_response>",
130
+ "single_word": false,
131
+ "lstrip": false,
132
+ "rstrip": false,
133
+ "normalized": false,
134
+ "special": true
135
+ },
136
+ "51": {
137
+ "content": "<tool_response|>",
138
+ "single_word": false,
139
+ "lstrip": false,
140
+ "rstrip": false,
141
+ "normalized": false,
142
+ "special": true
143
+ },
144
+ "52": {
145
+ "content": "<|\"|>",
146
+ "single_word": false,
147
+ "lstrip": false,
148
+ "rstrip": false,
149
+ "normalized": false,
150
+ "special": true
151
+ },
152
+ "98": {
153
+ "content": "<|think|>",
154
+ "single_word": false,
155
+ "lstrip": false,
156
+ "rstrip": false,
157
+ "normalized": false,
158
+ "special": true
159
+ },
160
+ "100": {
161
+ "content": "<|channel>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ "101": {
169
+ "content": "<channel|>",
170
+ "single_word": false,
171
+ "lstrip": false,
172
+ "rstrip": false,
173
+ "normalized": false,
174
+ "special": true
175
+ },
176
+ "105": {
177
+ "content": "<|turn>",
178
+ "single_word": false,
179
+ "lstrip": false,
180
+ "rstrip": false,
181
+ "normalized": false,
182
+ "special": true
183
+ },
184
+ "106": {
185
+ "content": "<turn|>",
186
+ "single_word": false,
187
+ "lstrip": false,
188
+ "rstrip": false,
189
+ "normalized": false,
190
+ "special": true
191
+ },
192
+ "255999": {
193
+ "content": "<|image>",
194
+ "single_word": false,
195
+ "lstrip": false,
196
+ "rstrip": false,
197
+ "normalized": false,
198
+ "special": true
199
+ },
200
+ "256000": {
201
+ "content": "<|audio>",
202
+ "single_word": false,
203
+ "lstrip": false,
204
+ "rstrip": false,
205
+ "normalized": false,
206
+ "special": true
207
+ },
208
+ "258880": {
209
+ "content": "<|image|>",
210
+ "single_word": false,
211
+ "lstrip": false,
212
+ "rstrip": false,
213
+ "normalized": false,
214
+ "special": true
215
+ },
216
+ "258881": {
217
+ "content": "<|audio|>",
218
+ "single_word": false,
219
+ "lstrip": false,
220
+ "rstrip": false,
221
+ "normalized": false,
222
+ "special": true
223
+ },
224
+ "258882": {
225
+ "content": "<image|>",
226
+ "single_word": false,
227
+ "lstrip": false,
228
+ "rstrip": false,
229
+ "normalized": false,
230
+ "special": true
231
+ },
232
+ "258883": {
233
+ "content": "<audio|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ "258884": {
241
+ "content": "<|video|>",
242
+ "single_word": false,
243
+ "lstrip": false,
244
+ "rstrip": false,
245
+ "normalized": false,
246
+ "special": true
247
+ }
248
+ }
249
+ }