daisy7942/python_basic_qa_dataset_model
018
1{
2 "architectures": [
3 "Gemma3ForConditionalGeneration"
4 ],
5 "boi_token_index": 255999,
6 "eoi_token_index": 256000,
7 "eos_token_id": [
8 1,
9 106
10 ],
11 "image_token_index": 262144,
12 "initializer_range": 0.02,
13 "mm_tokens_per_image": 256,
14 "model_type": "gemma3",
15 "text_config": {
16 "attention_bias": false,
17 "attention_dropout": 0.0,
18 "attn_logit_softcapping": null,
19 "cache_implementation": "hybrid",
20 "final_logit_softcapping": null,
21 "head_dim": 256,
22 "hidden_activation": "gelu_pytorch_tanh",
23 "hidden_size": 2560,
24 "initializer_range": 0.02,
25 "intermediate_size": 10240,
26 "max_position_embeddings": 131072,
27 "model_type": "gemma3_text",
28 "num_attention_heads": 8,
29 "num_hidden_layers": 34,
30 "num_key_value_heads": 4,
31 "query_pre_attn_scalar": 256,
32 "rms_norm_eps": 1e-06,
33 "rope_local_base_freq": 10000.0,
34 "rope_scaling": {
35 "factor": 8.0,
36 "rope_type": "linear"
37 },
38 "rope_theta": 1000000.0,
39 "sliding_window": 1024,
40 "sliding_window_pattern": 6,
41 "torch_dtype": "bfloat16",
42 "use_cache": true,
43 "vocab_size": 262208
44 },
45 "torch_dtype": "bfloat16",
46 "transformers_version": "4.51.3",
47 "vision_config": {
48 "attention_dropout": 0.0,
49 "hidden_act": "gelu_pytorch_tanh",
50 "hidden_size": 1152,
51 "image_size": 896,
52 "intermediate_size": 4304,
53 "layer_norm_eps": 1e-06,
54 "model_type": "siglip_vision_model",
55 "num_attention_heads": 16,
56 "num_channels": 3,
57 "num_hidden_layers": 27,
58 "patch_size": 14,
59 "torch_dtype": "bfloat16",
60 "vision_use_head": false
61 }
62}
63 