Files
MAJESTIC-FIN-R1-gguf/config.json

77 lines
1.7 KiB
JSON
Raw Permalink Normal View History

{
"architectures": [
"Lfm2ForCausalLM"
],
"block_auto_adjust_ff_dim": false,
"block_dim": 2048,
"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,
"torch_dtype": "float16",
"eos_token_id": 7,
"full_attn_idxs": null,
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 10752,
"layer_types": [
"conv",
"conv",
"full_attention",
"conv",
"conv",
"full_attention",
"conv",
"conv",
"conv",
"full_attention",
"conv",
"conv",
"conv",
"full_attention",
"conv",
"conv",
"conv",
"full_attention",
"conv",
"conv",
"conv",
"full_attention",
"conv",
"conv",
"full_attention",
"conv",
"conv",
"full_attention",
"conv",
"conv"
],
"max_position_embeddings": 128000,
"model_name": "LiquidAI/LFM2-2.6B",
"model_type": "lfm2",
"norm_eps": 1e-05,
"num_attention_heads": 32,
"num_heads": 32,
"num_hidden_layers": 30,
"num_key_value_heads": 8,
"pad_token_id": 0,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"theta": 1000000.0,
"tie_word_embeddings": true,
"unsloth_version": "2026.4.8",
"use_cache": false,
"use_pos_enc": true,
"vocab_size": 65536
}