| { |
| "architectures": [ |
| "Gemma3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_logit_softcapping": null, |
| "bos_token_id": 2, |
| "cache_implementation": "hybrid", |
| "eos_token_id": 1, |
| "final_logit_softcapping": 30.0, |
| "head_dim": 128, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "layer_type": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 32768, |
| "model_type": "gemma3_text", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pad_token_id": 0, |
| "query_pre_attn_scalar": 128, |
| "rms_norm_eps": 1e-06, |
| "rope_local_base_freq": 10000, |
| "rope_scaling": { |
| "attn_factor": 1.0, |
| "beta_fast": 64.0, |
| "beta_slow": 1.0, |
| "extrapolation_factor": 1.0, |
| "factor": 4.0, |
| "original_max_position_embeddings": 8192, |
| "rope_type": "yarn" |
| }, |
| "rope_theta": 10000, |
| "sliding_window": 32768, |
| "sliding_window_pattern": 1, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.2", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
