Hugging Face's logo

TiGa-RCE
/
LFM2-1.2B-MLX-oQ-Sweep

MLX
Safetensors
quantized
oq
lfm2
Model card Files
xet
 Community
LFM2-1.2B-MLX-oQ-Sweep
File size: 2,936 Bytes
100a4b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
{
  "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,
  "full_attn_idxs": [
    2,
    5,
    8,
    10,
    12,
    14
  ],
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "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,
  "rope_theta": 1000000.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.54.0.dev0",
  "use_cache": true,
  "use_pos_enc": true,
  "vocab_size": 65536,
  "quantization": {
    "group_size": 64,
    "bits": 2,
    "mode": "affine",
    "model.embed_tokens": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.0.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.1.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.10.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.11.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.12.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.13.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.14.self_attn.k_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    }
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 2,
    "mode": "affine",
    "model.embed_tokens": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.0.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.1.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.10.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.11.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.12.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.13.feed_forward.w2": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.layers.14.self_attn.k_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    }
  }
}