devops-thiago/classone-gemma4-e4b

1{
2  "architectures": [
3    "Gemma4Model"
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    "dtype": "float16",
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  "dtype": "float16",
49  "eoa_token_id": 258883,
50  "eoa_token_index": 258883,
51  "eoi_token_id": 258882,
52  "eos_token_id": [
53    1,
54    106
55  ],
56  "image_token_id": 258880,
57  "initializer_range": 0.02,
58  "model_type": "gemma4",
59  "text_config": {
60    "attention_bias": false,
61    "attention_dropout": 0.0,
62    "attention_k_eq_v": false,
63    "bos_token_id": 2,
64    "dtype": "float16",
65    "enable_moe_block": false,
66    "eos_token_id": 1,
67    "expert_intermediate_size": null,
68    "final_logit_softcapping": 30.0,
69    "head_dim": 256,
70    "hidden_activation": "gelu_pytorch_tanh",
71    "hidden_size": 2560,
72    "hidden_size_per_layer_input": 256,
73    "initializer_range": 0.02,
74    "intermediate_size": 10240,
75    "layer_types": [
76      "sliding_attention",
77      "sliding_attention",
78      "sliding_attention",
79      "sliding_attention",
80      "sliding_attention",
81      "full_attention",
82      "sliding_attention",
83      "sliding_attention",
84      "sliding_attention",
85      "sliding_attention",
86      "sliding_attention",
87      "full_attention",
88      "sliding_attention",
89      "sliding_attention",
90      "sliding_attention",
91      "sliding_attention",
92      "sliding_attention",
93      "full_attention",
94      "sliding_attention",
95      "sliding_attention",
96      "sliding_attention",
97      "sliding_attention",
98      "sliding_attention",
99      "full_attention",
100      "sliding_attention",
101      "sliding_attention",
102      "sliding_attention",
103      "sliding_attention",
104      "sliding_attention",
105      "full_attention",
106      "sliding_attention",
107      "sliding_attention",
108      "sliding_attention",
109      "sliding_attention",
110      "sliding_attention",
111      "full_attention",
112      "sliding_attention",
113      "sliding_attention",
114      "sliding_attention",
115      "sliding_attention",
116      "sliding_attention",
117      "full_attention"
118    ],
119    "max_position_embeddings": 131072,
120    "model_type": "gemma4_text",
121    "moe_intermediate_size": null,
122    "num_attention_heads": 8,
123    "num_experts": null,
124    "num_hidden_layers": 42,
125    "num_key_value_heads": 2,
126    "num_kv_shared_layers": 18,
127    "pad_token_id": 0,
128    "per_layer_config": {
129      "05": {
130        "head_dim": 512
131      },
132      "11": {
133        "head_dim": 512
134      },
135      "17": {
136        "head_dim": 512
137      },
138      "23": {
139        "head_dim": 512
140      },
141      "29": {
142        "head_dim": 512
143      },
144      "35": {
145        "head_dim": 512
146      },
147      "41": {
148        "head_dim": 512
149      }
150    },
151    "rms_norm_eps": 1e-06,
152    "rope_parameters": {
153      "full_attention": {
154        "partial_rotary_factor": 0.25,
155        "rope_theta": 1000000.0,
156        "rope_type": "proportional"
157      },
158      "sliding_attention": {
159        "rope_theta": 10000.0,
160        "rope_type": "default"
161      }
162    },
163    "sliding_window": 512,
164    "tie_word_embeddings": true,
165    "top_k_experts": null,
166    "use_bidirectional_attention": null,
167    "use_cache": true,
168    "use_double_wide_mlp": false,
169    "vocab_size": 262144,
170    "vocab_size_per_layer_input": 262144
171  },
172  "tie_word_embeddings": true,
173  "transformers_version": "5.17.0",
174  "video_token_id": 258884,
175  "vision_config": {
176    "_name_or_path": "",
177    "architectures": null,
178    "attention_bias": false,
179    "attention_dropout": 0.0,
180    "chunk_size_feed_forward": 0,
181    "default_output_length": 280,
182    "dtype": "float16",
183    "global_head_dim": 64,
184    "head_dim": 64,
185    "hidden_activation": "gelu_pytorch_tanh",
186    "hidden_size": 768,
187    "id2label": {
188      "0": "LABEL_0",
189      "1": "LABEL_1"
190    },
191    "initializer_range": 0.02,
192    "intermediate_size": 3072,
193    "is_encoder_decoder": false,
194    "label2id": {
195      "LABEL_0": 0,
196      "LABEL_1": 1
197    },
198    "max_position_embeddings": 131072,
199    "model_type": "gemma4_vision",
200    "num_attention_heads": 12,
201    "num_hidden_layers": 16,
202    "num_key_value_heads": 12,
203    "output_attentions": false,
204    "output_hidden_states": false,
205    "patch_size": 16,
206    "pooling_kernel_size": 3,
207    "position_embedding_size": 10240,
208    "problem_type": null,
209    "return_dict": true,
210    "rms_norm_eps": 1e-06,
211    "rope_parameters": {
212      "rope_theta": 100.0,
213      "rope_type": "axial"
214    },
215    "standardize": false,
216    "use_clipped_linears": true
217  },
218  "vision_soft_tokens_per_image": 280
219}
220