Hugging Face's logo

nvidia
/
Cosmos3-Super-Image2Video

Image-to-Video
Cosmos
Diffusers
Safetensors
cosmos3_omni
nvidia
cosmos3
vllm-omni
sglang
sglang-diffusion
video-generation
Model card Files
xet
 Community
5
Cosmos3-Super-Image2Video
File size: 4,854 Bytes
0835988
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
180
181
182
183
184
185
{
    "block_quantize": null,
    "calib_cfg": {
        "method": "max"
    },
    "channel_quantize": null,
    "disable_conv_quantization": false,
    "forward_loop": null,
    "modelopt_config": {
        "algorithm": "max",
        "quant_cfg": [
            {
                "enable": false,
                "quantizer_name": "*"
            },
            {
                "cfg": {
                    "axis": null,
                    "fake_quant": false,
                    "num_bits": [
                        4,
                        3
                    ]
                },
                "quantizer_name": "*weight_quantizer"
            },
            {
                "cfg": {
                    "axis": null,
                    "num_bits": [
                        4,
                        3
                    ]
                },
                "quantizer_name": "*input_quantizer"
            },
            {
                "enable": false,
                "parent_class": "nn.BatchNorm1d",
                "quantizer_name": "*"
            },
            {
                "enable": false,
                "parent_class": "nn.BatchNorm2d",
                "quantizer_name": "*"
            },
            {
                "enable": false,
                "parent_class": "nn.BatchNorm3d",
                "quantizer_name": "*"
            },
            {
                "enable": false,
                "parent_class": "nn.LeakyReLU",
                "quantizer_name": "*"
            },
            {
                "enable": false,
                "quantizer_name": "*lm_head*"
            },
            {
                "enable": false,
                "quantizer_name": "*proj_out.*"
            },
            {
                "enable": false,
                "quantizer_name": "*block_sparse_moe.gate*"
            },
            {
                "enable": false,
                "quantizer_name": "*router*"
            },
            {
                "enable": false,
                "quantizer_name": "*mlp.gate.*"
            },
            {
                "enable": false,
                "quantizer_name": "*mlp.shared_expert_gate.*"
            },
            {
                "enable": false,
                "quantizer_name": "*linear_attn.conv1d*"
            },
            {
                "enable": false,
                "quantizer_name": "*mixer.conv1d*"
            },
            {
                "enable": false,
                "quantizer_name": "*output_layer*"
            },
            {
                "enable": false,
                "quantizer_name": "output.*"
            },
            {
                "enable": false,
                "quantizer_name": "*proj_in*"
            },
            {
                "enable": false,
                "quantizer_name": "*proj_out*"
            },
            {
                "enable": false,
                "quantizer_name": "*time_embedder*"
            },
            {
                "enable": false,
                "quantizer_name": "*audio_proj_in*"
            },
            {
                "enable": false,
                "quantizer_name": "*audio_proj_out*"
            },
            {
                "enable": false,
                "quantizer_name": "*action_proj_in*"
            },
            {
                "enable": false,
                "quantizer_name": "*action_proj_out*"
            },
            {
                "enable": false,
                "quantizer_name": "*lm_head*"
            },
            {
                "enable": false,
                "quantizer_name": "*visual*"
            }
        ]
    },
    "modules_to_not_convert": [
        "proj_in",
        "proj_out",
        "time_embedder",
        "audio_proj_in",
        "audio_proj_out",
        "action_proj_in",
        "action_proj_out",
        "lm_head",
        "visual"
    ],
    "quant_method": "modelopt",
    "quant_type": "FP8_FP8",
    "scale_block_quantize": null,
    "scale_channel_quantize": null,
    "weight_only": false,
    "config_groups": {
        "group_0": {
            "input_activations": {
                "dynamic": false,
                "num_bits": 8,
                "type": "float"
            },
            "weights": {
                "dynamic": false,
                "num_bits": 8,
                "type": "float"
            },
            "targets": [
                "Linear"
            ]
        }
    },
    "quant_algo": "FP8",
    "ignore": [
        "proj_in",
        "proj_out",
        "time_embedder*",
        "audio_proj_in",
        "audio_proj_out",
        "action_proj_in",
        "action_proj_out",
        "lm_head",
        "model.visual*",
        "visual*"
    ],
    "producer": {
        "name": "modelopt",
        "version": "0.44.0"
    }
}