text_encoder/config.json
| 1 | { |
| 2 | "architectures": [ |
| 3 | "Gemma3ForConditionalGeneration" |
| 4 | ], |
| 5 | "boi_token_index": 255999, |
| 6 | "dtype": "float32", |
| 7 | "eoi_token_index": 256000, |
| 8 | "eos_token_id": [ |
| 9 | 1, |
| 10 | 106 |
| 11 | ], |
| 12 | "image_token_index": 262144, |
| 13 | "initializer_range": 0.02, |
| 14 | "mm_tokens_per_image": 256, |
| 15 | "model_type": "gemma3", |
| 16 | "text_config": { |
| 17 | "_sliding_window_pattern": 6, |
| 18 | "attention_bias": false, |
| 19 | "attention_dropout": 0.0, |
| 20 | "attn_logit_softcapping": null, |
| 21 | "cache_implementation": "hybrid", |
| 22 | "dtype": "float32", |
| 23 | "final_logit_softcapping": null, |
| 24 | "head_dim": 256, |
| 25 | "hidden_activation": "gelu_pytorch_tanh", |
| 26 | "hidden_size": 3840, |
| 27 | "initializer_range": 0.02, |
| 28 | "intermediate_size": 15360, |
| 29 | "layer_types": [ |
| 30 | "sliding_attention", |
| 31 | "sliding_attention", |
| 32 | "sliding_attention", |
| 33 | "sliding_attention", |
| 34 | "sliding_attention", |
| 35 | "full_attention", |
| 36 | "sliding_attention", |
| 37 | "sliding_attention", |
| 38 | "sliding_attention", |
| 39 | "sliding_attention", |
| 40 | "sliding_attention", |
| 41 | "full_attention", |
| 42 | "sliding_attention", |
| 43 | "sliding_attention", |
| 44 | "sliding_attention", |
| 45 | "sliding_attention", |
| 46 | "sliding_attention", |
| 47 | "full_attention", |
| 48 | "sliding_attention", |
| 49 | "sliding_attention", |
| 50 | "sliding_attention", |
| 51 | "sliding_attention", |
| 52 | "sliding_attention", |
| 53 | "full_attention", |
| 54 | "sliding_attention", |
| 55 | "sliding_attention", |
| 56 | "sliding_attention", |
| 57 | "sliding_attention", |
| 58 | "sliding_attention", |
| 59 | "full_attention", |
| 60 | "sliding_attention", |
| 61 | "sliding_attention", |
| 62 | "sliding_attention", |
| 63 | "sliding_attention", |
| 64 | "sliding_attention", |
| 65 | "full_attention", |
| 66 | "sliding_attention", |
| 67 | "sliding_attention", |
| 68 | "sliding_attention", |
| 69 | "sliding_attention", |
| 70 | "sliding_attention", |
| 71 | "full_attention", |
| 72 | "sliding_attention", |
| 73 | "sliding_attention", |
| 74 | "sliding_attention", |
| 75 | "sliding_attention", |
| 76 | "sliding_attention", |
| 77 | "full_attention" |
| 78 | ], |
| 79 | "max_position_embeddings": 131072, |
| 80 | "model_type": "gemma3_text", |
| 81 | "num_attention_heads": 16, |
| 82 | "num_hidden_layers": 48, |
| 83 | "num_key_value_heads": 8, |
| 84 | "query_pre_attn_scalar": 256, |
| 85 | "rms_norm_eps": 1e-06, |
| 86 | "rope_local_base_freq": 10000, |
| 87 | "rope_scaling": { |
| 88 | "factor": 8.0, |
| 89 | "rope_type": "linear" |
| 90 | }, |
| 91 | "rope_theta": 1000000, |
| 92 | "sliding_window": 1024, |
| 93 | "sliding_window_pattern": 6, |
| 94 | "use_bidirectional_attention": false, |
| 95 | "use_cache": true, |
| 96 | "vocab_size": 262208 |
| 97 | }, |
| 98 | "transformers_version": "4.57.3", |
| 99 | "vision_config": { |
| 100 | "attention_dropout": 0.0, |
| 101 | "dtype": "float32", |
| 102 | "hidden_act": "gelu_pytorch_tanh", |
| 103 | "hidden_size": 1152, |
| 104 | "image_size": 896, |
| 105 | "intermediate_size": 4304, |
| 106 | "layer_norm_eps": 1e-06, |
| 107 | "model_type": "siglip_vision_model", |
| 108 | "num_attention_heads": 16, |
| 109 | "num_channels": 3, |
| 110 | "num_hidden_layers": 27, |
| 111 | "patch_size": 14, |
| 112 | "vision_use_head": false |
| 113 | } |
| 114 | } |
| 115 | |