File size: 1,628 Bytes
b806295
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "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": 128000,
    "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": {
        "group_size": 32,
        "bits": 6,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 32,
        "bits": 6,
        "mode": "affine"
    },
    "rope_theta": 1000000.0,
    "theta": 1000000.0,
    "tie_embedding": true,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.54.1",
    "use_cache": true,
    "use_pos_enc": true,
    "vocab_size": 65536
}