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,
  "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": 32768,
  "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": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": [
      "embed_tokens",
      "embedding",
      "lm_head",
      "multi_modal_projector",
      "merger",
      "modality_projection",
      "conv"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rope_theta": 1000000.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.54.0.dev0",
  "unsloth_fixed": true,
  "use_cache": true,
  "use_pos_enc": true,
  "vocab_size": 65536
}