FP8 checkpoint for Cosmos3-Nano
#23
by wkutak - opened
- hf_quant_config.json +185 -0
- model.safetensors.index.json +0 -0
- transformer/config.json +212 -1
- transformer/{diffusion_pytorch_model-00001-of-00007.safetensors → diffusion_pytorch_model-00001-of-00004.safetensors} +2 -2
- transformer/{diffusion_pytorch_model-00002-of-00007.safetensors → diffusion_pytorch_model-00002-of-00004.safetensors} +2 -2
- transformer/{diffusion_pytorch_model-00003-of-00007.safetensors → diffusion_pytorch_model-00003-of-00004.safetensors} +2 -2
- transformer/{diffusion_pytorch_model-00004-of-00007.safetensors → diffusion_pytorch_model-00004-of-00004.safetensors} +2 -2
- transformer/diffusion_pytorch_model-00005-of-00007.safetensors +0 -3
- transformer/diffusion_pytorch_model-00006-of-00007.safetensors +0 -3
- transformer/diffusion_pytorch_model-00007-of-00007.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": 64,
|
| 5 |
"action_gen": true,
|
| 6 |
"attention_bias": false,
|
|
@@ -29,7 +29,218 @@
|
|
| 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": 64,
|
| 5 |
"action_gen": true,
|
| 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 |
+
"runtime": {
|
| 180 |
+
"diffusion_step_policy": {
|
| 181 |
+
"schema_version": 1,
|
| 182 |
+
"type": "first_last_n",
|
| 183 |
+
"index_space": "denoising_loop_iteration",
|
| 184 |
+
"scope": [
|
| 185 |
+
"transformer"
|
| 186 |
+
],
|
| 187 |
+
"default_mode": "native",
|
| 188 |
+
"first_steps": {
|
| 189 |
+
"count": 3,
|
| 190 |
+
"mode": "a16"
|
| 191 |
+
},
|
| 192 |
+
"last_steps": {
|
| 193 |
+
"count": 3,
|
| 194 |
+
"mode": "a16"
|
| 195 |
+
},
|
| 196 |
+
"overlap": "a16",
|
| 197 |
+
"reasoner": "a16"
|
| 198 |
+
}
|
| 199 |
+
},
|
| 200 |
+
"scale_block_quantize": null,
|
| 201 |
+
"scale_channel_quantize": null,
|
| 202 |
+
"weight_only": false,
|
| 203 |
+
"config_groups": {
|
| 204 |
+
"group_0": {
|
| 205 |
+
"input_activations": {
|
| 206 |
+
"dynamic": false,
|
| 207 |
+
"num_bits": 8,
|
| 208 |
+
"type": "float"
|
| 209 |
+
},
|
| 210 |
+
"weights": {
|
| 211 |
+
"dynamic": false,
|
| 212 |
+
"num_bits": 8,
|
| 213 |
+
"type": "float"
|
| 214 |
+
},
|
| 215 |
+
"targets": [
|
| 216 |
+
"Linear"
|
| 217 |
+
]
|
| 218 |
+
}
|
| 219 |
+
},
|
| 220 |
+
"quant_algo": "FP8",
|
| 221 |
+
"ignore": [
|
| 222 |
+
"proj_in",
|
| 223 |
+
"proj_out",
|
| 224 |
+
"time_embedder*",
|
| 225 |
+
"audio_proj_in",
|
| 226 |
+
"audio_proj_out",
|
| 227 |
+
"action_proj_in",
|
| 228 |
+
"action_proj_out",
|
| 229 |
+
"lm_head",
|
| 230 |
+
"model.visual*",
|
| 231 |
+
"visual*"
|
| 232 |
+
],
|
| 233 |
+
"producer": {
|
| 234 |
+
"name": "modelopt",
|
| 235 |
+
"version": "0.44.0"
|
| 236 |
+
}
|
| 237 |
+
},
|
| 238 |
"rms_norm_eps": 1e-06,
|
| 239 |
+
"rope_axes_dim": [
|
| 240 |
+
24,
|
| 241 |
+
20,
|
| 242 |
+
20
|
| 243 |
+
],
|
| 244 |
"rope_scaling": {
|
| 245 |
"mrope_interleaved": true,
|
| 246 |
"mrope_section": [
|
transformer/{diffusion_pytorch_model-00001-of-00007.safetensors → diffusion_pytorch_model-00001-of-00004.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 sha256:5140edb1b67c8593b7c6edeffb037fbd3607483e0d9dc91c57e513fc5ca29e9e
|
| 3 |
+
size 4970103116
|
transformer/{diffusion_pytorch_model-00002-of-00007.safetensors → diffusion_pytorch_model-00002-of-00004.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 sha256:65fb34e75b2275fe08067463b42d692ed374860d0559ab2a76c395df1438734b
|
| 3 |
+
size 4999955300
|
transformer/{diffusion_pytorch_model-00003-of-00007.safetensors → diffusion_pytorch_model-00003-of-00004.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:b70cfc2244820aa2b9936b313cb5341c838d87e9eae9f00ec3136b94c2ba61b3
|
| 3 |
+
size 4992824672
|
transformer/{diffusion_pytorch_model-00004-of-00007.safetensors → diffusion_pytorch_model-00004-of-00004.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:f186eb1543b3ca55cf427d5677d745801eb942295e02de4ffe723c5c5e3cc770
|
| 3 |
+
size 1493278920
|
transformer/diffusion_pytorch_model-00005-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a5e3edd742b8f1fcf27a3eb3878c67dfcb0e6881588fa35deef503d640ea69d1
|
| 3 |
-
size 4949498576
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00006-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1bb99750f7ab4a47f8b0403a87aa43fefc9648660609ab2ace4cab361b957cd0
|
| 3 |
-
size 4261644464
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model-00007-of-00007.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3f159bc8b82477adde771ae9e4f54f76564e02844a2fc6267903bd745111d7f6
|
| 3 |
-
size 1318361208
|
|
|
|
|
|
|
|
|
|
|
|
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 sha256:1b31e0f686e3df50eb7b45aca990f939b912f5e62b2a9ed125677a29311f0b97
|
| 3 |
+
size 451799
|