| { |
| "activation_sparsity_pattern": [ |
| 0.95, |
| 0.95 |
| ], |
| "altup_active_idx": 0, |
| "altup_coef_clip": 120.0, |
| "altup_correct_scale": true, |
| "altup_num_inputs": 4, |
| "architectures": [ |
| "Gemma3nForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 2, |
| "dtype": "float32", |
| "eos_token_id": 1, |
| "final_logit_softcapping": 30.0, |
| "head_dim": 8, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 64, |
| "hidden_size_per_layer_input": 1, |
| "initializer_range": 0.02, |
| "intermediate_size": [ |
| 128, |
| 128 |
| ], |
| "laurel_rank": 8, |
| "layer_types": [ |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 2048, |
| "model_type": "gemma3n_text", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "num_kv_shared_layers": 0, |
| "pad_token_id": 0, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "full_attention": { |
| "rope_theta": 1000000.0, |
| "rope_type": "default" |
| }, |
| "sliding_attention": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "sliding_window": 512, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.0.0", |
| "use_cache": true, |
| "vocab_size": 262400, |
| "vocab_size_per_layer_input": 262144 |
| } |
|
|
