Text-to-Image
Cosmos
Diffusers
Safetensors
cosmos3_omni
nvidia
cosmos3
vllm-omni
sglang
sglang-diffusion
image-generation
Instructions to use nvidia/Cosmos3-Super-Text2Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Super-Text2Image with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Diffusers
How to use nvidia/Cosmos3-Super-Text2Image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/Cosmos3-Super-Text2Image", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add Cosmos3 Super Text2Image FP8 checkpoint
#18
by wkutak - opened
- hf_quant_config.json +185 -0
- model.safetensors.index.json +0 -0
- transformer/config.json +191 -1
- transformer/{diffusion_pytorch_model-00001-of-00027.safetensors → diffusion_pytorch_model-00001-of-00014.safetensors} +2 -2
- transformer/{diffusion_pytorch_model-00002-of-00027.safetensors → diffusion_pytorch_model-00002-of-00014.safetensors} +2 -2
- transformer/{diffusion_pytorch_model-00003-of-00027.safetensors → diffusion_pytorch_model-00003-of-00014.safetensors} +2 -2
- transformer/{diffusion_pytorch_model-00004-of-00027.safetensors → diffusion_pytorch_model-00004-of-00014.safetensors} +2 -2
- transformer/diffusion_pytorch_model-00005-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00005-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00006-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00006-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00007-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00007-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00008-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00008-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00009-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00009-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00010-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00010-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00011-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00011-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00012-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00012-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00013-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00013-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00014-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00014-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00015-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00016-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00017-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00018-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00019-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00020-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00021-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00022-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00023-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00024-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00025-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00026-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model-00027-of-00027.safetensors +0 -3
- transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
- transformer/modelopt_state.pth +3 -0
hf_quant_config.json
ADDED
|
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"block_quantize": null,
|
| 3 |
+
"calib_cfg": {
|
| 4 |
+
"method": "max"
|
| 5 |
+
},
|
| 6 |
+
"channel_quantize": null,
|
| 7 |
+
"disable_conv_quantization": false,
|
| 8 |
+
"forward_loop": null,
|
| 9 |
+
"modelopt_config": {
|
| 10 |
+
"algorithm": "max",
|
| 11 |
+
"quant_cfg": [
|
| 12 |
+
{
|
| 13 |
+
"enable": false,
|
| 14 |
+
"quantizer_name": "*"
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"cfg": {
|
| 18 |
+
"axis": null,
|
| 19 |
+
"fake_quant": false,
|
| 20 |
+
"num_bits": [
|
| 21 |
+
4,
|
| 22 |
+
3
|
| 23 |
+
]
|
| 24 |
+
},
|
| 25 |
+
"quantizer_name": "*weight_quantizer"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"cfg": {
|
| 29 |
+
"axis": null,
|
| 30 |
+
"num_bits": [
|
| 31 |
+
4,
|
| 32 |
+
3
|
| 33 |
+
]
|
| 34 |
+
},
|
| 35 |
+
"quantizer_name": "*input_quantizer"
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"enable": false,
|
| 39 |
+
"parent_class": "nn.BatchNorm1d",
|
| 40 |
+
"quantizer_name": "*"
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"enable": false,
|
| 44 |
+
"parent_class": "nn.BatchNorm2d",
|
| 45 |
+
"quantizer_name": "*"
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"enable": false,
|
| 49 |
+
"parent_class": "nn.BatchNorm3d",
|
| 50 |
+
"quantizer_name": "*"
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"enable": false,
|
| 54 |
+
"parent_class": "nn.LeakyReLU",
|
| 55 |
+
"quantizer_name": "*"
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"enable": false,
|
| 59 |
+
"quantizer_name": "*lm_head*"
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"enable": false,
|
| 63 |
+
"quantizer_name": "*proj_out.*"
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"enable": false,
|
| 67 |
+
"quantizer_name": "*block_sparse_moe.gate*"
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"enable": false,
|
| 71 |
+
"quantizer_name": "*router*"
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"enable": false,
|
| 75 |
+
"quantizer_name": "*mlp.gate.*"
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"enable": false,
|
| 79 |
+
"quantizer_name": "*mlp.shared_expert_gate.*"
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"enable": false,
|
| 83 |
+
"quantizer_name": "*linear_attn.conv1d*"
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"enable": false,
|
| 87 |
+
"quantizer_name": "*mixer.conv1d*"
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"enable": false,
|
| 91 |
+
"quantizer_name": "*output_layer*"
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"enable": false,
|
| 95 |
+
"quantizer_name": "output.*"
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"enable": false,
|
| 99 |
+
"quantizer_name": "*proj_in*"
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"enable": false,
|
| 103 |
+
"quantizer_name": "*proj_out*"
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"enable": false,
|
| 107 |
+
"quantizer_name": "*time_embedder*"
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"enable": false,
|
| 111 |
+
"quantizer_name": "*audio_proj_in*"
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"enable": false,
|
| 115 |
+
"quantizer_name": "*audio_proj_out*"
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"enable": false,
|
| 119 |
+
"quantizer_name": "*action_proj_in*"
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"enable": false,
|
| 123 |
+
"quantizer_name": "*action_proj_out*"
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"enable": false,
|
| 127 |
+
"quantizer_name": "*lm_head*"
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"enable": false,
|
| 131 |
+
"quantizer_name": "*visual*"
|
| 132 |
+
}
|
| 133 |
+
]
|
| 134 |
+
},
|
| 135 |
+
"modules_to_not_convert": [
|
| 136 |
+
"proj_in",
|
| 137 |
+
"proj_out",
|
| 138 |
+
"time_embedder",
|
| 139 |
+
"audio_proj_in",
|
| 140 |
+
"audio_proj_out",
|
| 141 |
+
"action_proj_in",
|
| 142 |
+
"action_proj_out",
|
| 143 |
+
"lm_head",
|
| 144 |
+
"visual"
|
| 145 |
+
],
|
| 146 |
+
"quant_method": "modelopt",
|
| 147 |
+
"quant_type": "FP8_FP8",
|
| 148 |
+
"scale_block_quantize": null,
|
| 149 |
+
"scale_channel_quantize": null,
|
| 150 |
+
"weight_only": false,
|
| 151 |
+
"config_groups": {
|
| 152 |
+
"group_0": {
|
| 153 |
+
"input_activations": {
|
| 154 |
+
"dynamic": false,
|
| 155 |
+
"num_bits": 8,
|
| 156 |
+
"type": "float"
|
| 157 |
+
},
|
| 158 |
+
"weights": {
|
| 159 |
+
"dynamic": false,
|
| 160 |
+
"num_bits": 8,
|
| 161 |
+
"type": "float"
|
| 162 |
+
},
|
| 163 |
+
"targets": [
|
| 164 |
+
"Linear"
|
| 165 |
+
]
|
| 166 |
+
}
|
| 167 |
+
},
|
| 168 |
+
"quant_algo": "FP8",
|
| 169 |
+
"ignore": [
|
| 170 |
+
"proj_in",
|
| 171 |
+
"proj_out",
|
| 172 |
+
"time_embedder*",
|
| 173 |
+
"audio_proj_in",
|
| 174 |
+
"audio_proj_out",
|
| 175 |
+
"action_proj_in",
|
| 176 |
+
"action_proj_out",
|
| 177 |
+
"lm_head",
|
| 178 |
+
"model.visual*",
|
| 179 |
+
"visual*"
|
| 180 |
+
],
|
| 181 |
+
"producer": {
|
| 182 |
+
"name": "modelopt",
|
| 183 |
+
"version": "0.44.0"
|
| 184 |
+
}
|
| 185 |
+
}
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "Cosmos3OmniTransformer",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"action_dim": 32,
|
| 5 |
"action_gen": false,
|
| 6 |
"attention_bias": false,
|
|
@@ -29,7 +29,197 @@
|
|
| 29 |
"qk_norm": false,
|
| 30 |
"qk_norm_for_diffusion": true,
|
| 31 |
"qk_norm_for_text": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"rms_norm_eps": 1e-06,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
"rope_scaling": {
|
| 34 |
"mrope_interleaved": true,
|
| 35 |
"mrope_section": [
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "Cosmos3OmniTransformer",
|
| 3 |
+
"_diffusers_version": "0.39.0",
|
| 4 |
"action_dim": 32,
|
| 5 |
"action_gen": false,
|
| 6 |
"attention_bias": false,
|
|
|
|
| 29 |
"qk_norm": false,
|
| 30 |
"qk_norm_for_diffusion": true,
|
| 31 |
"qk_norm_for_text": true,
|
| 32 |
+
"quantization_config": {
|
| 33 |
+
"block_quantize": null,
|
| 34 |
+
"calib_cfg": {
|
| 35 |
+
"method": "max"
|
| 36 |
+
},
|
| 37 |
+
"channel_quantize": null,
|
| 38 |
+
"disable_conv_quantization": false,
|
| 39 |
+
"forward_loop": null,
|
| 40 |
+
"modelopt_config": {
|
| 41 |
+
"algorithm": "max",
|
| 42 |
+
"quant_cfg": [
|
| 43 |
+
{
|
| 44 |
+
"enable": false,
|
| 45 |
+
"quantizer_name": "*"
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"cfg": {
|
| 49 |
+
"axis": null,
|
| 50 |
+
"fake_quant": false,
|
| 51 |
+
"num_bits": [
|
| 52 |
+
4,
|
| 53 |
+
3
|
| 54 |
+
]
|
| 55 |
+
},
|
| 56 |
+
"quantizer_name": "*weight_quantizer"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"cfg": {
|
| 60 |
+
"axis": null,
|
| 61 |
+
"num_bits": [
|
| 62 |
+
4,
|
| 63 |
+
3
|
| 64 |
+
]
|
| 65 |
+
},
|
| 66 |
+
"quantizer_name": "*input_quantizer"
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"enable": false,
|
| 70 |
+
"parent_class": "nn.BatchNorm1d",
|
| 71 |
+
"quantizer_name": "*"
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"enable": false,
|
| 75 |
+
"parent_class": "nn.BatchNorm2d",
|
| 76 |
+
"quantizer_name": "*"
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"enable": false,
|
| 80 |
+
"parent_class": "nn.BatchNorm3d",
|
| 81 |
+
"quantizer_name": "*"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"enable": false,
|
| 85 |
+
"parent_class": "nn.LeakyReLU",
|
| 86 |
+
"quantizer_name": "*"
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"enable": false,
|
| 90 |
+
"quantizer_name": "*lm_head*"
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"enable": false,
|
| 94 |
+
"quantizer_name": "*proj_out.*"
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"enable": false,
|
| 98 |
+
"quantizer_name": "*block_sparse_moe.gate*"
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"enable": false,
|
| 102 |
+
"quantizer_name": "*router*"
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"enable": false,
|
| 106 |
+
"quantizer_name": "*mlp.gate.*"
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"enable": false,
|
| 110 |
+
"quantizer_name": "*mlp.shared_expert_gate.*"
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"enable": false,
|
| 114 |
+
"quantizer_name": "*linear_attn.conv1d*"
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"enable": false,
|
| 118 |
+
"quantizer_name": "*mixer.conv1d*"
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"enable": false,
|
| 122 |
+
"quantizer_name": "*output_layer*"
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"enable": false,
|
| 126 |
+
"quantizer_name": "output.*"
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"enable": false,
|
| 130 |
+
"quantizer_name": "*proj_in*"
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"enable": false,
|
| 134 |
+
"quantizer_name": "*proj_out*"
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"enable": false,
|
| 138 |
+
"quantizer_name": "*time_embedder*"
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"enable": false,
|
| 142 |
+
"quantizer_name": "*audio_proj_in*"
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"enable": false,
|
| 146 |
+
"quantizer_name": "*audio_proj_out*"
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"enable": false,
|
| 150 |
+
"quantizer_name": "*action_proj_in*"
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"enable": false,
|
| 154 |
+
"quantizer_name": "*action_proj_out*"
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"enable": false,
|
| 158 |
+
"quantizer_name": "*lm_head*"
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"enable": false,
|
| 162 |
+
"quantizer_name": "*visual*"
|
| 163 |
+
}
|
| 164 |
+
]
|
| 165 |
+
},
|
| 166 |
+
"modules_to_not_convert": [
|
| 167 |
+
"proj_in",
|
| 168 |
+
"proj_out",
|
| 169 |
+
"time_embedder",
|
| 170 |
+
"audio_proj_in",
|
| 171 |
+
"audio_proj_out",
|
| 172 |
+
"action_proj_in",
|
| 173 |
+
"action_proj_out",
|
| 174 |
+
"lm_head",
|
| 175 |
+
"visual"
|
| 176 |
+
],
|
| 177 |
+
"quant_method": "modelopt",
|
| 178 |
+
"quant_type": "FP8_FP8",
|
| 179 |
+
"scale_block_quantize": null,
|
| 180 |
+
"scale_channel_quantize": null,
|
| 181 |
+
"weight_only": false,
|
| 182 |
+
"config_groups": {
|
| 183 |
+
"group_0": {
|
| 184 |
+
"input_activations": {
|
| 185 |
+
"dynamic": false,
|
| 186 |
+
"num_bits": 8,
|
| 187 |
+
"type": "float"
|
| 188 |
+
},
|
| 189 |
+
"weights": {
|
| 190 |
+
"dynamic": false,
|
| 191 |
+
"num_bits": 8,
|
| 192 |
+
"type": "float"
|
| 193 |
+
},
|
| 194 |
+
"targets": [
|
| 195 |
+
"Linear"
|
| 196 |
+
]
|
| 197 |
+
}
|
| 198 |
+
},
|
| 199 |
+
"quant_algo": "FP8",
|
| 200 |
+
"ignore": [
|
| 201 |
+
"proj_in",
|
| 202 |
+
"proj_out",
|
| 203 |
+
"time_embedder*",
|
| 204 |
+
"audio_proj_in",
|
| 205 |
+
"audio_proj_out",
|
| 206 |
+
"action_proj_in",
|
| 207 |
+
"action_proj_out",
|
| 208 |
+
"lm_head",
|
| 209 |
+
"model.visual*",
|
| 210 |
+
"visual*"
|
| 211 |
+
],
|
| 212 |
+
"producer": {
|
| 213 |
+
"name": "modelopt",
|
| 214 |
+
"version": "0.44.0"
|
| 215 |
+
}
|
| 216 |
+
},
|
| 217 |
"rms_norm_eps": 1e-06,
|
| 218 |
+
"rope_axes_dim": [
|
| 219 |
+
24,
|
| 220 |
+
20,
|
| 221 |
+
20
|
| 222 |
+
],
|
| 223 |
"rope_scaling": {
|
| 224 |
"mrope_interleaved": true,
|
| 225 |
"mrope_section": [
|
transformer/{diffusion_pytorch_model-00001-of-00027.safetensors → diffusion_pytorch_model-00001-of-00014.safetensors}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82cdecebf76f121909af2d04f7ef54d4a89b096ccffd68837b1845dd7b56b3da
|
| 3 |
+
size 4874967684
|
transformer/{diffusion_pytorch_model-00002-of-00027.safetensors → diffusion_pytorch_model-00002-of-00014.safetensors}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd437eb7bc8062e18d034b655b53d1ac36009044400c155679439369f4821e50
|
| 3 |
+
size 4975501784
|
transformer/{diffusion_pytorch_model-00003-of-00027.safetensors → diffusion_pytorch_model-00003-of-00014.safetensors}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8294c05fb2087e1edf956fb8b709a1c9bb9177b23d5c0bca46436dd0aacb9562
|
| 3 |
+
size 4965490244
|
transformer/{diffusion_pytorch_model-00004-of-00027.safetensors → diffusion_pytorch_model-00004-of-00014.safetensors}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef57868bb434c98b995039c8ce4ccb29df54d67ea0cba35472aa98a3b27a2e6
|
| 3 |
+
size 4959772504
|
transformer/diffusion_pytorch_model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cf263d62a747108803b5f0ba4d858168bcca143726b4a9334597fe383a50d9e
|
| 3 |
+
size 4996946796
|
transformer/diffusion_pytorch_model-00005-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ca34444e30ecd797c7a8065d3501abd02125039c9601e14864b089cb9834b92b
|
| 3 |
-
size 4949368096
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd551fff6a435525e3907ce2011c55224dd355c4744b347cc07021ca3f0f4b4
|
| 3 |
+
size 4934076892
|
transformer/diffusion_pytorch_model-00006-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:57ab33ceb73ce02a014acecfbf812d09f7a43c0f4a5b327b206276e61f0ba826
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c218a38d1f14979917f8201b380dd93441cfa8810c959a84fc6b6f3b5da8616
|
| 3 |
+
size 4959772528
|
transformer/diffusion_pytorch_model-00007-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b83bb25e88ae2197ba33d5b192d0a81aac40cdebfdfb7ca048271a5718fd8edc
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b05e942f1039d98906992f8ef31126319b5ad328070e4dbc823f45af4d85596
|
| 3 |
+
size 4970258840
|
transformer/diffusion_pytorch_model-00008-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a48a7b2aa7e99160e028f9818709e8b575c95dddc2c6a38cde99d7eb488c1ec9
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5403f8765ff2d54d91b8908a955c1eafbfad3b9d0e0bb25d349f723342bf3b47
|
| 3 |
+
size 4960249044
|
transformer/diffusion_pytorch_model-00009-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:63737abe6c08976075e7f9c53e56a7d64ac92bb12078e9aeac47d48146a8786c
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca7aef60a8ad9392b97815cc354aa6e01cdb966be1ca29045e27aed624ce69ae
|
| 3 |
+
size 4975501856
|
transformer/diffusion_pytorch_model-00010-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:42ab03b9b949e82e454df3e235a6ae649f4bc531549c0df9b7e6a680abbf9fb3
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:983735f1bc2e101ae1020a65b32799e9bb578e9e53e7a133d885599bab9681df
|
| 3 |
+
size 4907817796
|
transformer/diffusion_pytorch_model-00011-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:03be6e218bc83d193bf2baf88c9ce9b011156003c43e16b5fa35935e761c0680
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d2fb313efabfc9bd7af99ff87208be2e438f080ea404c1f846f1ba6c6e41cf4
|
| 3 |
+
size 4975501856
|
transformer/diffusion_pytorch_model-00012-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b317d06f0adb826b962c11c28d04bdc8866ee4ae20b5538b4bbda8092654ee0e
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715bd80e3abe320a4a35dd943c49346b203f72f8d640040f2f3c967e6c45422b
|
| 3 |
+
size 4971861504
|
transformer/diffusion_pytorch_model-00013-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d6513f5245c13752bf675241e35995cebd8d3e774a5dc139e8fbbe2842345c96
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ba6ef712609da140d960ea21f235e4f0b2a3bb4d49615d27b4e419803f748d0
|
| 3 |
+
size 1158857928
|
transformer/diffusion_pytorch_model-00014-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:bdc20ad60439a6684fb2b5d63da8b44b6bd2907916f109de253d4e8264242dfc
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00015-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3af6c17c430cac5b768f23f1ae6fc92061846719e19d5d4c24f4be397daa07b9
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00016-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0a65c367ac5c7f39695205e7c91e6e1afd5c8e6283e52e894afe124aa122e6ea
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00017-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0296852ac2e05e56519a90825684bd37640e7debeb329f29c6a4760f79762ee4
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00018-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f078e14b01727f24fa03e5715708a5a2f676b97d264bcc8bc91166d74830d5b0
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00019-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:009765e7b69ffe65de8e14b026e9cd998d1d463aab687b895844c0d82855699d
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00020-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c55e2e02da62cd9ad77dcbf4b4f759d620976c663c7a7953132ece1c43560863
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00021-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:340e4a0066591985390b649ddfbf705adb7bf1235c963223e8291cd0a44e9b78
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00022-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4d019a64084a0294c89d7ad4ed2ad177b03278550ce68f390fa2c036845a6250
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00023-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f5b974d3465abcf072fba5c37ae2147f612a2467d82cd38a199facc99e23ca16
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00024-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:06cf61bdb7560b4392f1ee025561e57215dd3b59a39414a41a58e42dca34cbd0
|
| 3 |
-
size 4802611024
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00025-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9f93556b82a598a4bb39b12aff60a4784f7fb8545e1e91e4ffe6f84d6f29a11f
|
| 3 |
-
size 4949368104
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00026-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a2aeef5aa284fb8a083f703bf7803628a47f819aa934328fce7a4a44c2b27d4d
|
| 3 |
-
size 4425141960
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00027-of-00027.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d3cf9a5eca4234cc33d42d950cbaf9984d5663fb7808ab03c63fa5a5a49d0125
|
| 3 |
-
size 1616160480
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/modelopt_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcc268801c2a315f4061027a3b6d2166ecca2de81db287a60cfafebf2189a7ab
|
| 3 |
+
size 798423
|