| { |
| "architectures": [ |
| "Gemma3ForConditionalGeneration" |
| ], |
| "boi_token_index": 255999, |
| "dtype": "float32", |
| "eoi_token_index": 256000, |
| "eos_token_id": [ |
| 1, |
| 106 |
| ], |
| "image_token_index": 262144, |
| "initializer_range": 0.02, |
| "mm_tokens_per_image": 4, |
| "model_type": "gemma3", |
| "text_config": { |
| "_sliding_window_pattern": 6, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_logit_softcapping": null, |
| "bos_token_id": 2, |
| "eos_token_id": 1, |
| "final_logit_softcapping": null, |
| "head_dim": 16, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 64, |
| "initializer_range": 0.02, |
| "intermediate_size": 32, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention" |
| ], |
| "max_position_embeddings": 131072, |
| "model_type": "gemma3_text", |
| "num_attention_heads": 4, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "pad_token_id": 0, |
| "query_pre_attn_scalar": 256, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "full_attention": { |
| "factor": 8.0, |
| "rope_theta": 1000000.0, |
| "rope_type": "linear" |
| }, |
| "rope_theta": null, |
| "rope_type": "default", |
| "sliding_attention": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "sliding_window": 1024, |
| "tie_word_embeddings": true, |
| "use_bidirectional_attention": false, |
| "use_cache": true, |
| "vocab_size": 262208 |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.3.0.dev0", |
| "vision_config": { |
| "attention_dropout": 0.0, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 64, |
| "image_size": 28, |
| "intermediate_size": 32, |
| "layer_norm_eps": 1e-06, |
| "model_type": "siglip_vision_model", |
| "num_attention_heads": 4, |
| "num_channels": 3, |
| "num_hidden_layers": 2, |
| "patch_size": 14, |
| "vision_use_head": false |
| }, |
| "transformers.js_config": { |
| "use_external_data_format": { |
| "vision_encoder.onnx": 1, |
| "decoder_model_merged.onnx": 1, |
| "embed_tokens.onnx": 1, |
| "vision_encoder_fp16.onnx": 1, |
| "decoder_model_merged_fp16.onnx": 1, |
| "embed_tokens_fp16.onnx": 1 |
| }, |
| "kv_cache_dtype": { |
| "q4f16": "float16", |
| "fp16": "float16" |
| } |
| } |
| } |
