suryatmodulus/LFM2.5-Encoder-350M-Prompt-Router

1{2  "architectures": [3    "Lfm2BidirForSequenceRouting"4  ],5  "auto_map": {6    "AutoModel": "modeling_lfm2_bidirectional.Lfm2BidirForSequenceRouting",7    "AutoModelForMaskedLM": "modeling_lfm2_bidirectional.Lfm2BidirectionalForMaskedLM"8  },9  "block_auto_adjust_ff_dim": true,10  "block_dim": 1024,11  "block_ffn_dim_multiplier": 1.0,12  "block_mlp_init_scale": 1.0,13  "block_multiple_of": 256,14  "block_norm_eps": 1e-05,15  "block_out_init_scale": 1.0,16  "block_use_swiglu": true,17  "block_use_xavier_init": true,18  "bos_token_id": 1,19  "conv_L_cache": 3,20  "conv_bias": false,21  "conv_dim": 1024,22  "conv_dim_out": 1024,23  "conv_use_xavier_init": true,24  "dtype": "float32",25  "eos_token_id": 7,26  "hidden_size": 1024,27  "initializer_range": 0.02,28  "intermediate_size": 6656,29  "layer_types": [30    "conv",31    "conv",32    "full_attention",33    "conv",34    "conv",35    "full_attention",36    "conv",37    "conv",38    "full_attention",39    "conv",40    "full_attention",41    "conv",42    "full_attention",43    "conv",44    "full_attention",45    "conv"46  ],47  "max_position_embeddings": 128000,48  "model_type": "lfm2",49  "norm_eps": 1e-05,50  "num_attention_heads": 16,51  "num_heads": 16,52  "num_hidden_layers": 16,53  "num_key_value_heads": 8,54  "pad_token_id": 0,55  "rope_parameters": {56    "rope_theta": 1000000.0,57    "rope_type": "default"58  },59  "rule_proj_dim": 256,60  "tie_word_embeddings": true,61  "transformers_version": "5.1.0",62  "use_cache": false,63  "use_pos_enc": true,64  "vocab_size": 6553665}66