| { |
| "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": null, |
| "head_dim": 256, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 10240, |
| "max_position_embeddings": 131072, |
| "model_type": "gemma3_text", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 34, |
| "num_key_value_heads": 4, |
| "pad_token_id": 0, |
| "query_pre_attn_scalar": 256, |
| "rms_norm_eps": 1e-06, |
| "rope_local_base_freq": 10000.0, |
| "rope_scaling": { |
| "factor": 8.0, |
| "rope_type": "linear" |
| }, |
| "rope_theta": 1000000.0, |
| "sliding_window": 1024, |
| "sliding_window_pattern": 6, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "use_cache": false, |
| "vocab_size": 262208 |
| } |
|
|
