config.json

{
  "architectures": [
    "Lfm2ForCausalLM"
  ],
  "block__name_mlp": "parallel_mlp_merged",
  "block_auto_adjust_ff_dim": false,
  "block_dim": 1024,
  "block_ff_dim": 2560,
  "block_ffn_dim_multiplier": 1.0,
  "block_ffn_te_autocast": false,
  "block_ffn_use_quantized_params": false,
  "block_mlp_init_scale": 1.0,
  "block_multiple_of": 256,
  "block_norm_eps": 1e-05,
  "block_out_init_scale": 1.0,
  "block_sequence_parallel_norm_across_tp": false,
  "block_use_swiglu": true,
  "block_use_xavier_init": true,
  "bos_token_id": 1,
  "conv_L_cache": 3,
  "conv_bias": false,
  "conv_dim": 1024,
  "conv_use_xavier_init": true,
  "dtype": "bfloat16",
  "eos_token_id": 7,
  "ffn_te_autocast": false,
  "ffn_use_quantized_params": false,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 2560,
  "layer_types": [
    "conv",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv",
    "full_attention",
    "conv"
  ],
  "max_position_embeddings": 128000,
  "model_type": "lfm2",
  "norm_eps": 1e-05,
  "num_attention_heads": 16,
  "num_heads": 16,
  "num_hidden_layers": 14,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "sequence_parallel_norm_across_tp": false,
  "tie_embedding": true,
  "tie_word_embeddings": true,
  "transformers_version": "5.2.0",
  "use_cache": true,
  "use_pos_enc": true,
  "vocab_size": 65536
}