File size: 2,966 Bytes
f164a88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
{
    "architectures": [
        "Lfm2VlForConditionalGeneration"
    ],
    "do_image_splitting": true,
    "downsample_factor": 2,
    "torch_dtype": "float16",
    "encoder_patch_size": 16,
    "image_token_id": 396,
    "max_image_tokens": 256,
    "max_pixels_tolerance": 2.0,
    "max_tiles": 10,
    "min_image_tokens": 64,
    "min_tiles": 2,
    "model_name": "LiquidAI/LFM2.5-VL-450M",
    "model_type": "lfm2_vl",
    "pad_token_id": 0,
    "projector_bias": true,
    "projector_hidden_act": "gelu",
    "projector_hidden_size": 2048,
    "projector_use_layernorm": false,
    "text_config": {
        "_name_or_path": "LiquidAI/LFM2-350M",
        "architectures": [
            "Lfm2ForCausalLM"
        ],
        "block_auto_adjust_ff_dim": true,
        "block_dim": 1024,
        "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": 1024,
        "conv_dim_out": 1024,
        "conv_use_xavier_init": true,
        "torch_dtype": "float16",
        "eos_token_id": 7,
        "full_attn_idxs": null,
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 6656,
        "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": 16,
        "num_heads": 16,
        "num_hidden_layers": 16,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "rope_parameters": {
            "rope_theta": 1000000.0,
            "rope_type": "default"
        },
        "tie_word_embeddings": true,
        "use_cache": true,
        "use_pos_enc": true,
        "vocab_size": 65536
    },
    "tie_word_embeddings": true,
    "tile_size": 512,
    "unsloth_version": "2026.4.4",
    "use_cache": false,
    "use_image_special_tokens": true,
    "use_thumbnail": true,
    "vision_config": {
        "attention_dropout": 0.0,
        "torch_dtype": "float16",
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 768,
        "intermediate_size": 3072,
        "layer_norm_eps": 1e-06,
        "model_type": "siglip2_vision_model",
        "num_attention_heads": 12,
        "num_channels": 3,
        "num_hidden_layers": 12,
        "num_patches": 256,
        "patch_size": 16,
        "vision_use_head": false
    }
}