Hugging Face's logo

nm-testing
/
granite-4.0-h-small-FP8-dynamic

Text Generation
Safetensors
granitemoehybrid
fp8
quantized
llm-compressor
compressed-tensors
red hat
conversational
Model card Files
xet
Community
granite-4.0-h-small-FP8-dynamic
File size: 5,293 Bytes 
eec5871
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
 
{
  "architectures": [
    "GraniteMoeHybridForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_multiplier": 0.0078125,
  "bos_token_id": 100257,
  "dtype": "bfloat16",
  "embedding_multiplier": 12,
  "eos_token_id": 100257,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.1,
  "intermediate_size": 768,
  "layer_types": [
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba"
  ],
  "logits_scaling": 16,
  "mamba_chunk_size": 256,
  "mamba_conv_bias": true,
  "mamba_d_conv": 4,
  "mamba_d_head": 64,
  "mamba_d_state": 128,
  "mamba_expand": 2,
  "mamba_n_groups": 1,
  "mamba_n_heads": 128,
  "mamba_proj_bias": false,
  "max_position_embeddings": 131072,
  "model_type": "granitemoehybrid",
  "normalization_function": "rmsnorm",
  "num_attention_heads": 32,
  "num_experts_per_tok": 10,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "num_local_experts": 72,
  "output_router_logits": false,
  "pad_token_id": 100256,
  "position_embedding_type": "nope",
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "float-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "token",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "channel",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.block_sparse_moe.router.layer",
      "model.layers.1.block_sparse_moe.router.layer",
      "model.layers.2.block_sparse_moe.router.layer",
      "model.layers.3.block_sparse_moe.router.layer",
      "model.layers.4.block_sparse_moe.router.layer",
      "model.layers.5.block_sparse_moe.router.layer",
      "model.layers.6.block_sparse_moe.router.layer",
      "model.layers.7.block_sparse_moe.router.layer",
      "model.layers.8.block_sparse_moe.router.layer",
      "model.layers.9.block_sparse_moe.router.layer",
      "model.layers.10.block_sparse_moe.router.layer",
      "model.layers.11.block_sparse_moe.router.layer",
      "model.layers.12.block_sparse_moe.router.layer",
      "model.layers.13.block_sparse_moe.router.layer",
      "model.layers.14.block_sparse_moe.router.layer",
      "model.layers.15.block_sparse_moe.router.layer",
      "model.layers.16.block_sparse_moe.router.layer",
      "model.layers.17.block_sparse_moe.router.layer",
      "model.layers.18.block_sparse_moe.router.layer",
      "model.layers.19.block_sparse_moe.router.layer",
      "model.layers.20.block_sparse_moe.router.layer",
      "model.layers.21.block_sparse_moe.router.layer",
      "model.layers.22.block_sparse_moe.router.layer",
      "model.layers.23.block_sparse_moe.router.layer",
      "model.layers.24.block_sparse_moe.router.layer",
      "model.layers.25.block_sparse_moe.router.layer",
      "model.layers.26.block_sparse_moe.router.layer",
      "model.layers.27.block_sparse_moe.router.layer",
      "model.layers.28.block_sparse_moe.router.layer",
      "model.layers.29.block_sparse_moe.router.layer",
      "model.layers.30.block_sparse_moe.router.layer",
      "model.layers.31.block_sparse_moe.router.layer",
      "model.layers.32.block_sparse_moe.router.layer",
      "model.layers.33.block_sparse_moe.router.layer",
      "model.layers.34.block_sparse_moe.router.layer",
      "model.layers.35.block_sparse_moe.router.layer",
      "model.layers.36.block_sparse_moe.router.layer",
      "model.layers.37.block_sparse_moe.router.layer",
      "model.layers.38.block_sparse_moe.router.layer",
      "model.layers.39.block_sparse_moe.router.layer",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.3.dev28+g2763f81"
  },
  "residual_multiplier": 0.22,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000,
  "router_aux_loss_coef": 0.0,
  "shared_intermediate_size": 1536,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "vocab_size": 100352
}