Hugging Face's logo

thinkingmachines
/
Inkling-NVFP4

Image-Text-to-Text
Transformers
Safetensors
inkling_mm_model
conversational
audio-text-to-text
Mixture of Experts
8-bit precision
Model card Files
xet
 Community
2
Inkling-NVFP4
File size: 2,415 Bytes
93a182f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "architectures": [
    "InklingForConditionalGeneration"
  ],
  "model_type": "inkling_mm_model",
  "eos_token_id": 200006,
  "text_config": {
    "model_max_length": 1048576,
    "torch_dtype": "bfloat16",
    "hidden_size": 6144,
    "num_hidden_layers": 66,
    "vocab_size": 201024,
    "num_attention_heads": 64,
    "num_key_value_heads": 8,
    "head_dim": 128,
    "d_rel": 16,
    "rel_extent": 1024,
    "q_bias": false,
    "o_bias": false,
    "log_scaling_n_floor": 128000,
    "log_scaling_alpha": 0.1,
    "rms_norm_eps": 1e-06,
    "use_embed_norm": true,
    "local_layer_ids": [
      0,
      1,
      2,
      3,
      4,
      6,
      7,
      8,
      9,
      10,
      12,
      13,
      14,
      15,
      16,
      18,
      19,
      20,
      21,
      22,
      24,
      25,
      26,
      27,
      28,
      30,
      31,
      32,
      33,
      34,
      36,
      37,
      38,
      39,
      40,
      42,
      43,
      44,
      45,
      46,
      48,
      49,
      50,
      51,
      52,
      54,
      55,
      56,
      57,
      58,
      60,
      61,
      62,
      63,
      64
    ],
    "dense_mlp_idx": 2,
    "use_sconv": true,
    "sconv_kernel_size": 4,
    "unpadded_vocab_size": 200058,
    "logits_mup_width_multiplier": 24.0,
    "final_logit_softcapping": null,
    "swa_head_dim": 128,
    "swa_num_attention_heads": 64,
    "swa_num_key_value_heads": 16,
    "sliding_window_size": 512,
    "n_routed_experts": 256,
    "num_experts_per_tok": 6,
    "n_shared_experts": 2,
    "shared_expert_sink": true,
    "dense_intermediate_size": 24576,
    "intermediate_size": 3072,
    "route_scale": 8.0,
    "use_gate_bias": true,
    "gate_activation": "sigmoid",
    "norm_after_topk": true,
    "use_global_scale": true
  },
  "audio_config": {
    "decoder_dmodel": 6144,
    "n_mel_bins": 80,
    "mel_vocab_size": 16,
    "bias": false,
    "dmel_min_value": -7.0,
    "dmel_max_value": 2.0,
    "use_audio_norm": true,
    "audio_mode": "dmel"
  },
  "vision_config": {
    "vision_encoder_type": "hmlp",
    "decoder_dmodel": 6144,
    "patch_size": 40,
    "temporal_patch_size": 2,
    "n_channels": 3,
    "n_layers": 4,
    "use_vision_norm": true
  },
  "mtp_config": {
    "num_nextn_predict_layers": 8,
    "chain_hidden_post_norm": false,
    "local_layer_ids": [
      0,
      2,
      4,
      5,
      6,
      7
    ]
  }
}