| { |
| "architectures": [ |
| "Gemma4ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_k_eq_v": false, |
| "bos_token_id": 2, |
| "dtype": "bfloat16", |
| "enable_moe_block": true, |
| "eos_token_id": 1, |
| "final_logit_softcapping": null, |
| "global_head_dim": 96, |
| "head_dim": 48, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 384, |
| "hidden_size_per_layer_input": 64, |
| "initializer_range": 0.02, |
| "intermediate_size": 1024, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 2048, |
| "model_type": "gemma4_text", |
| "moe_intermediate_size": 256, |
| "num_attention_heads": 8, |
| "num_experts": 4, |
| "num_global_key_value_heads": null, |
| "num_hidden_layers": 3, |
| "num_key_value_heads": 4, |
| "num_kv_shared_layers": 0, |
| "pad_token_id": 0, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "full_attention": { |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 1000000.0, |
| "rope_type": "proportional" |
| }, |
| "sliding_attention": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "sliding_window": 512, |
| "tie_word_embeddings": true, |
| "top_k_experts": 2, |
| "transformers_version": "5.5.0", |
| "use_bidirectional_attention": null, |
| "use_cache": true, |
| "use_double_wide_mlp": false, |
| "vocab_size": 50257, |
| "vocab_size_per_layer_input": 50257 |
| } |
|
|
