config.json

{
    "architectures": [
        "Lfm2ForCausalLM"
    ],
    "block_auto_adjust_ff_dim": true,
    "block_dim": 2048,
    "block_ff_dim": 12288,
    "block_ffn_dim_multiplier": 1.0,
    "block_mlp_init_scale": 1.0,
    "block_multiple_of": 256,
    "block_norm_eps": 1e-05,
    "block_out_init_scale": 1.0,
    "block_use_swiglu": true,
    "block_use_xavier_init": true,
    "bos_token_id": 1,
    "conv_L_cache": 3,
    "conv_bias": false,
    "conv_dim": 2048,
    "conv_dim_out": 2048,
    "conv_use_xavier_init": true,
    "eos_token_id": 7,
    "full_attn_idxs": [
        2,
        5,
        8,
        10,
        12,
        14
    ],
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "max_position_embeddings": 128000,
    "model_type": "lfm2",
    "norm_eps": 1e-05,
    "num_attention_heads": 32,
    "num_heads": 32,
    "num_hidden_layers": 16,
    "num_key_value_heads": 8,
    "pad_token_id": 0,
    "quantization": {
        "group_size": 64,
        "bits": 4
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4
    },
    "rope_theta": 1000000.0,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.54.0.dev0",
    "use_cache": true,
    "use_pos_enc": true,
    "vocab_size": 65536
}