| { |
| "architectures": [ |
| "Gemma3Pi06ForConditionalGeneration" |
| ], |
| "attn_implementation": null, |
| "auto_map": { |
| "AutoConfig": "configuration_gemma3_pi06.Gemma3Pi06Config", |
| "AutoModelForImageTextToText": "modeling_gemma3_pi06.Gemma3Pi06ForConditionalGeneration" |
| }, |
| "boi_token_index": 255999, |
| "dtype": "float32", |
| "eoi_token_index": 256000, |
| "image_token_index": 262144, |
| "initializer_range": 0.02, |
| "llm_base_model": "google/gemma-3-270m", |
| "mm_tokens_per_image": 256, |
| "model_type": "gemma3", |
| "model_variant": "pi06", |
| "text_config": { |
| "_sliding_window_pattern": 6, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_logit_softcapping": null, |
| "dtype": "bfloat16", |
| "final_logit_softcapping": null, |
| "head_dim": 256, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 640, |
| "initializer_range": 0.02, |
| "intermediate_size": 2048, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 32768, |
| "model_type": "gemma3_text", |
| "num_attention_heads": 4, |
| "num_hidden_layers": 18, |
| "num_key_value_heads": 1, |
| "query_pre_attn_scalar": 256, |
| "rms_norm_eps": 1e-06, |
| "rope_local_base_freq": 10000.0, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sliding_window": 512, |
| "use_bidirectional_attention": false, |
| "use_cache": true, |
| "vocab_size": 262208 |
| }, |
| "transformers_version": "4.57.1", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "image_size": 896, |
| "intermediate_size": 4304, |
| "layer_norm_eps": 1e-06, |
| "model_type": "siglip_vision_model", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 27, |
| "patch_size": 14, |
| "vision_use_head": false |
| }, |
| "vlm_base_model": "google/gemma-3-4b-pt" |
| } |
|
|
