Hugging Face's logo

Sawfwair
/
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-MLX

Text Generation
MLX
Safetensors
PyTorch
nemotron_h
mere-run
nvidia
nemotron-3.5
conversational
Model card Files
xet
 Community
1
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-MLX
File size: 2,769 Bytes
cfd0243
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": [
    "NemotronHForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "chunk_size": 128,
  "conv_kernel": 4,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "expand": 2,
  "head_dim": 128,
  "hidden_dropout": 0.0,
  "hidden_size": 2688,
  "initializer_range": 0.02,
  "intermediate_size": 1856,
  "layer_norm_epsilon": 1e-05,
  "layers_block_type": [
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "attention",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "attention",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "attention",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "attention",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "attention",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "attention",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe",
    "mamba",
    "moe"
  ],
  "mamba_head_dim": 64,
  "mamba_hidden_act": "silu",
  "mamba_num_heads": 64,
  "mamba_proj_bias": false,
  "mamba_ssm_cache_dtype": "float32",
  "max_position_embeddings": 1048576,
  "mlp_bias": false,
  "mlp_hidden_act": "relu2",
  "mlx_conversion": {
    "fp8": "released-e4m3-values-materialized-as-bfloat16",
    "mtp": "omitted-in-favor-of-managed-dspark-companion",
    "nvfp4": "bit-exact-repack-with-retained-global-scale",
    "source_format": "modelopt-mixed-nvfp4-fp8"
  },
  "model_type": "nemotron_h",
  "moe_intermediate_size": 1856,
  "moe_latent_size": null,
  "moe_shared_expert_intermediate_size": 3712,
  "moe_shared_expert_overlap": true,
  "mtp_layers_block_type": [
    "attention",
    "moe"
  ],
  "n_group": 1,
  "n_groups": 8,
  "n_routed_experts": 128,
  "n_shared_experts": 1,
  "norm_eps": 1e-05,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 52,
  "num_key_value_heads": 2,
  "num_logits_to_keep": 1,
  "num_nextn_predict_layers": 1,
  "pad_token_id": 0,
  "partial_rotary_factor": 1.0,
  "quantization": {
    "bits": 4,
    "global_scale": true,
    "group_size": 16,
    "mode": "nvfp4",
    "scope": "routed-and-shared-experts-plus-lm-head"
  },
  "rescale_prenorm_residual": true,
  "residual_in_fp32": false,
  "rope_theta": 10000,
  "routed_scaling_factor": 2.5,
  "sliding_window": null,
  "ssm_state_size": 128,
  "tie_word_embeddings": false,
  "time_step_floor": 0.0001,
  "time_step_max": 0.1,
  "time_step_min": 0.001,
  "topk_group": 1,
  "transformers_version": "5.8.1",
  "use_bias": false,
  "use_cache": true,
  "use_conv_bias": true,
  "use_mamba_kernels": true,
  "vocab_size": 131072
}