{ "architectures": [ "Gemma2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": 50.0, "bos_token_id": 2, "dtype": "bfloat16", "eos_token_id": 1, "final_logit_softcapping": 30.0, "head_dim": 128, "hidden_act": "gelu_pytorch_tanh", "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 4608, "initializer_range": 0.02, "intermediate_size": 36864, "layer_types": [ "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 32768, "model_type": "gemma2", "num_attention_heads": 32, "num_hidden_layers": 46, "num_key_value_heads": 16, "pad_token_id": 0, "query_pre_attn_scalar": 144, "rms_norm_eps": 1e-06, "rope_parameters": { "factor": 4.0, "original_max_position_embeddings": 8192, "rope_theta": 10000.0, "rope_type": "yarn", "type": "yarn" }, "sliding_window": 4096, "tie_word_embeddings": true, "transformers_version": "5.3.0", "use_bidirectional_attention": null, "use_cache": true, "vocab_size": 256000 }