devops-thiago/classone-gemma4-e2b

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": 1536,
72    "hidden_size_per_layer_input": 256,
73    "initializer_range": 0.02,
74    "intermediate_size": 6144,
75    "layer_types": [
76      "sliding_attention",
77      "sliding_attention",
78      "sliding_attention",
79      "sliding_attention",
80      "full_attention",
81      "sliding_attention",
82      "sliding_attention",
83      "sliding_attention",
84      "sliding_attention",
85      "full_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      "full_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      "full_attention",
106      "sliding_attention",
107      "sliding_attention",
108      "sliding_attention",
109      "sliding_attention",
110      "full_attention"
111    ],
112    "max_position_embeddings": 131072,
113    "model_type": "gemma4_text",
114    "moe_intermediate_size": null,
115    "num_attention_heads": 8,
116    "num_experts": null,
117    "num_hidden_layers": 35,
118    "num_key_value_heads": 1,
119    "num_kv_shared_layers": 20,
120    "pad_token_id": 0,
121    "per_layer_config": {
122      "04": {
123        "head_dim": 512
124      },
125      "09": {
126        "head_dim": 512
127      },
128      "14": {
129        "head_dim": 512
130      },
131      "19": {
132        "head_dim": 512
133      },
134      "24": {
135        "head_dim": 512
136      },
137      "29": {
138        "head_dim": 512
139      },
140      "34": {
141        "head_dim": 512
142      }
143    },
144    "rms_norm_eps": 1e-06,
145    "rope_parameters": {
146      "full_attention": {
147        "partial_rotary_factor": 0.25,
148        "rope_theta": 1000000.0,
149        "rope_type": "proportional"
150      },
151      "sliding_attention": {
152        "rope_theta": 10000.0,
153        "rope_type": "default"
154      }
155    },
156    "sliding_window": 512,
157    "tie_word_embeddings": true,
158    "top_k_experts": null,
159    "use_bidirectional_attention": null,
160    "use_cache": true,
161    "use_double_wide_mlp": true,
162    "vocab_size": 262144,
163    "vocab_size_per_layer_input": 262144
164  },
165  "tie_word_embeddings": true,
166  "transformers_version": "5.17.0",
167  "video_token_id": 258884,
168  "vision_config": {
169    "_name_or_path": "",
170    "architectures": null,
171    "attention_bias": false,
172    "attention_dropout": 0.0,
173    "chunk_size_feed_forward": 0,
174    "default_output_length": 280,
175    "dtype": "float16",
176    "global_head_dim": 64,
177    "head_dim": 64,
178    "hidden_activation": "gelu_pytorch_tanh",
179    "hidden_size": 768,
180    "id2label": {
181      "0": "LABEL_0",
182      "1": "LABEL_1"
183    },
184    "initializer_range": 0.02,
185    "intermediate_size": 3072,
186    "is_encoder_decoder": false,
187    "label2id": {
188      "LABEL_0": 0,
189      "LABEL_1": 1
190    },
191    "max_position_embeddings": 131072,
192    "model_type": "gemma4_vision",
193    "num_attention_heads": 12,
194    "num_hidden_layers": 16,
195    "num_key_value_heads": 12,
196    "output_attentions": false,
197    "output_hidden_states": false,
198    "patch_size": 16,
199    "pooling_kernel_size": 3,
200    "position_embedding_size": 10240,
201    "problem_type": null,
202    "return_dict": true,
203    "rms_norm_eps": 1e-06,
204    "rope_parameters": {
205      "rope_theta": 100.0,
206      "rope_type": "axial"
207    },
208    "standardize": false,
209    "use_clipped_linears": true
210  },
211  "vision_soft_tokens_per_image": 280
212}
213