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_use_xavier_init": true,
  "dtype": "bfloat16",
  "eos_token_id": 7,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "layer_types": [
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "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": 32,
  "num_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "float-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "token",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "channel",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.conv.in_proj",
      "model.layers.0.conv.out_proj",
      "model.layers.1.conv.in_proj",
      "model.layers.1.conv.out_proj",
      "model.layers.3.conv.in_proj",
      "model.layers.3.conv.out_proj",
      "model.layers.4.conv.in_proj",
      "model.layers.4.conv.out_proj",
      "model.layers.6.conv.in_proj",
      "model.layers.6.conv.out_proj",
      "model.layers.7.conv.in_proj",
      "model.layers.7.conv.out_proj",
      "model.layers.9.conv.in_proj",
      "model.layers.9.conv.out_proj",
      "model.layers.11.conv.in_proj",
      "model.layers.11.conv.out_proj",
      "model.layers.13.conv.in_proj",
      "model.layers.13.conv.out_proj",
      "model.layers.15.conv.in_proj",
      "model.layers.15.conv.out_proj",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.13.1.dev0"
  },
  "rope_theta": 1000000.0,
  "tie_embedding": true,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "use_pos_enc": true,
  "vocab_size": 65536
}