Xlnk/sql
115
1{2 "architectures": [3 "Lfm2ForCausalLM"4 ],5 "block_auto_adjust_ff_dim": true,6 "block_dim": 2048,7 "block_ff_dim": 12288,8 "block_ffn_dim_multiplier": 1.0,9 "block_mlp_init_scale": 1.0,10 "block_multiple_of": 256,11 "block_norm_eps": 1e-05,12 "block_out_init_scale": 1.0,13 "block_use_swiglu": true,14 "block_use_xavier_init": true,15 "bos_token_id": 1,16 "conv_L_cache": 3,17 "conv_bias": false,18 "conv_dim": 2048,19 "conv_use_xavier_init": true,20 "dtype": "bfloat16",21 "eos_token_id": 7,22 "hidden_size": 2048,23 "initializer_range": 0.02,24 "intermediate_size": 12288,25 "layer_types": [26 "conv",27 "conv",28 "full_attention",29 "conv",30 "conv",31 "full_attention",32 "conv",33 "conv",34 "full_attention",35 "conv",36 "full_attention",37 "conv",38 "full_attention",39 "conv",40 "full_attention",41 "conv"42 ],43 "max_position_embeddings": 128000,44 "model_type": "lfm2",45 "norm_eps": 1e-05,46 "num_attention_heads": 32,47 "num_heads": 32,48 "num_hidden_layers": 16,49 "num_key_value_heads": 8,50 "pad_token_id": 0,51 "rope_theta": 1000000.0,52 "tie_embedding": true,53 "transformers_version": "4.57.2",54 "use_cache": true,55 "use_pos_enc": true,56 "vocab_size": 6553657}58 