config.json

{
  "architectures": [
    "Lfm2ForCausalLM"
  ],
  "block_auto_adjust_ff_dim": true,
  "block_ffn_dim_multiplier": 1.0,
  "block_multiple_of": 256,
  "bos_token_id": 1,
  "conv_L_cache": 3,
  "conv_bias": false,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "full_attn_idxs": [
    0,
    1,
    2,
    3,
    4,
    5,
    6,
    7
  ],
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 2048,
  "model_type": "lfm2",
  "norm_eps": 1e-05,
  "num_attention_heads": 8,
  "num_hidden_layers": 8,
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "quantization_config": {
    "autoround_version": "0.13.0",
    "bits": 4,
    "block_name_to_quantize": "model.layers",
    "data_type": "int",
    "group_size": 128,
    "low_gpu_mem_usage": true,
    "packing_format": "auto_round:auto_gptq",
    "quant_method": "auto-round",
    "seqlen": 1024,
    "sym": true
  },
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.10.2",
  "use_cache": true,
  "vocab_size": 50257
}