FastFlowLM/LFM2-1.2B-NPU2
0193
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_dim_out": 2048,20 "conv_use_xavier_init": true,21 "eos_token_id": 7,22 "intermediate_size": 8192,23 "full_attn_idxs": [24 2,25 5,26 8,27 10,28 12,29 1430 ],31 "hidden_size": 2048,32 "initializer_range": 0.02,33 "max_position_embeddings": 128000,34 "model_type": "lfm2",35 "norm_eps": 1e-05,36 "num_attention_heads": 32,37 "head_dim": 64,38 "num_heads": 32,39 "num_hidden_layers": 16,40 "num_key_value_heads": 8,41 "pad_token_id": 0,42 "rope_theta": 1000000.0,43 "torch_dtype": "bfloat16",44 "transformers_version": "4.54.0.dev0",45 "use_cache": true,46 "use_pos_enc": true,47 "addr_l_begin_mha": 20480,48 "addr_l_end_mha": 35328,49 "vocab_size": 65536,50 "flm_version": "0.9.24"51}52 