{ "architectures": [ "Llama4ForCausalLM" ], "attention_bias": false, "attention_chunk_size": 8192, "attention_dropout": 0.0, "attn_scale": 0.1, "attn_temperature_tuning": true, "bos_token_id": 1, "cache_implementation": "hybrid", "eos_token_id": 2, "floor_scale": 8192, "head_dim": 32, "hidden_act": "silu", "hidden_size": 384, "initializer_range": 0.02, "interleave_moe_layer_step": 1, "intermediate_size": 1024, "intermediate_size_mlp": 256, "max_position_embeddings": 512, "model_type": "llama4_text", "moe_layers": [ 0, 1, 2, 3, 4, 5 ], "no_rope_layers": [ 1, 1, 1, 0, 1, 1 ], "num_attention_heads": 4, "num_experts_per_tok": 1, "num_hidden_layers": 6, "num_key_value_heads": 4, "num_local_experts": 16, "output_router_logits": false, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.51.3", "use_cache": true, "use_qk_norm": true, "vocab_size": 58 }