{ "architectures": [ "Lfm2MoeForCausalLM" ], "bos_token_id": 1, "conv_L_cache": 3, "conv_bias": false, "dtype": "bfloat16", "eos_token_id": 7, "hidden_size": 64, "intermediate_size": 128, "layer_types": [ "conv", "conv", "full_attention" ], "max_position_embeddings": 128000, "model_type": "lfm2_moe", "moe_intermediate_size": 128, "norm_eps": 1e-05, "norm_topk_prob": true, "num_attention_heads": 2, "num_dense_layers": 2, "num_experts": 32, "num_experts_per_tok": 4, "num_hidden_layers": 3, "num_key_value_heads": 1, "pad_token_id": 0, "rope_parameters": { "rope_theta": 1000000.0, "rope_type": "default" }, "rope_theta": 1000000.0, "routed_scaling_factor": 1.0, "transformers_version": "5.0.0.dev0", "use_cache": true, "use_expert_bias": true, "vocab_size": 65536 }