Merlin-Research/Micro-Merlin-Experimental

1{2    "architectures": [3        "Lfm2ForCausalLM"4    ],5    "block_auto_adjust_ff_dim": true,6    "block_dim": 2048,7    "block_ffn_dim_multiplier": 1.0,8    "block_mlp_init_scale": 1.0,9    "block_multiple_of": 256,10    "block_norm_eps": 1e-05,11    "block_out_init_scale": 1.0,12    "block_use_swiglu": true,13    "block_use_xavier_init": true,14    "bos_token_id": 1,15    "conv_L_cache": 3,16    "conv_bias": false,17    "conv_dim": 2048,18    "conv_use_xavier_init": true,19    "torch_dtype": "float16",20    "eos_token_id": 7,21    "full_attn_idxs": null,22    "hidden_size": 2048,23    "initializer_range": 0.02,24    "intermediate_size": 12288,25    "layer_types": [26        "conv",27        "conv",28        "full_attention",29        "conv",30        "conv",31        "full_attention",32        "conv",33        "conv",34        "full_attention",35        "conv",36        "full_attention",37        "conv",38        "full_attention",39        "conv",40        "full_attention",41        "conv"42    ],43    "max_position_embeddings": 128000,44    "model_name": "LiquidAI/LFM2.5-1.2B-Thinking",45    "model_type": "lfm2",46    "norm_eps": 1e-05,47    "num_attention_heads": 32,48    "num_heads": 32,49    "num_hidden_layers": 16,50    "num_key_value_heads": 8,51    "pad_token_id": 0,52    "rope_parameters": {53        "rope_theta": 1000000.0,54        "rope_type": "default"55    },56    "tie_word_embeddings": true,57    "unsloth_version": "2026.7.2",58    "use_cache": true,59    "use_pos_enc": true,60    "vocab_size": 6553661}