mirror of
https://www.modelscope.cn/Wan-AI/Wan2.2-Animate-14B.git
synced 2026-04-02 19:12:58 +08:00
Upload to Wan-AI/Wan2.2-Animate-14B on ModelScope hub
This commit is contained in:
kelseye
22
.gitattributes
vendored
22
.gitattributes
vendored
@ -45,3 +45,25 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
models_t5_umt5-xxl-enc-bf16.pth filter=lfs diff=lfs merge=lfs -text
|
||||
google/umt5-xxl/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
Wan2.1_VAE.pth filter=lfs diff=lfs merge=lfs -text
|
||||
google/umt5-xxl/spiece.model filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/flax_model.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
diffusion_pytorch_model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/onnx/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/onnx/sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/tf_model.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
||||
diffusion_pytorch_model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
diffusion_pytorch_model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
diffusion_pytorch_model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
relighting_lora/adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/onnx/model.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
xlm-roberta-large/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth filter=lfs diff=lfs merge=lfs -text
|
||||
relighting_lora.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
3
Wan2.1_VAE.pth
Normal file
3
Wan2.1_VAE.pth
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:acf6c5aa49ad281d4b561e10656e2397c446a8ba4b8d8f19d3dd125c2628bc6a
|
||||
size 507609928
|
||||
30
config.json
Normal file
30
config.json
Normal file
@ -0,0 +1,30 @@
|
||||
{
|
||||
"__name__": "Config: Transformer config for WanAnimateModel",
|
||||
"_class_name": "WanAnimateModel",
|
||||
"_diffusers_version": "0.33.1",
|
||||
"_name_or_path": "Wan-animate",
|
||||
"cross_attn_norm": true,
|
||||
"dim": 5120,
|
||||
"eps": 1e-06,
|
||||
"ffn_dim": 13824,
|
||||
"freq_dim": 256,
|
||||
"in_dim": 36,
|
||||
"motion_encoder_dim": 512,
|
||||
"num_heads": 40,
|
||||
"num_layers": 40,
|
||||
"out_dim": 16,
|
||||
"patch_size": [
|
||||
1,
|
||||
2,
|
||||
2
|
||||
],
|
||||
"qk_norm": true,
|
||||
"text_dim": 4096,
|
||||
"text_len": 512,
|
||||
"use_context_parallel": false,
|
||||
"use_img_emb": true,
|
||||
"window_size": [
|
||||
-1,
|
||||
-1
|
||||
]
|
||||
}
|
||||
3
diffusion_pytorch_model-00001-of-00004.safetensors
Normal file
3
diffusion_pytorch_model-00001-of-00004.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:575c2dba750c3b40240fb742a4224453aa97dfbd3c5f5a0086be431cdefdd69c
|
||||
size 9875257880
|
||||
3
diffusion_pytorch_model-00002-of-00004.safetensors
Normal file
3
diffusion_pytorch_model-00002-of-00004.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b90b820627d43eeeb1ae0489182f9a8c870374fd72cc99dccb9eddfc2ace8325
|
||||
size 9975378288
|
||||
3
diffusion_pytorch_model-00003-of-00004.safetensors
Normal file
3
diffusion_pytorch_model-00003-of-00004.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e2aa343b0ba04f563566e9959a439611a18189cd9accdc04d59681be9ce5be50
|
||||
size 9954400528
|
||||
3
diffusion_pytorch_model-00004-of-00004.safetensors
Normal file
3
diffusion_pytorch_model-00004-of-00004.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e5fea7f38aa4cb70ed59a9ecf406d0c05f3dfc85ee70bc83de35679c42642d1b
|
||||
size 4744748472
|
||||
1448
diffusion_pytorch_model.safetensors.index.json
Normal file
1448
diffusion_pytorch_model.safetensors.index.json
Normal file
File diff suppressed because it is too large
Load Diff
308
google/umt5-xxl/special_tokens_map.json
Normal file
308
google/umt5-xxl/special_tokens_map.json
Normal file
@ -0,0 +1,308 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<extra_id_0>",
|
||||
"<extra_id_1>",
|
||||
"<extra_id_2>",
|
||||
"<extra_id_3>",
|
||||
"<extra_id_4>",
|
||||
"<extra_id_5>",
|
||||
"<extra_id_6>",
|
||||
"<extra_id_7>",
|
||||
"<extra_id_8>",
|
||||
"<extra_id_9>",
|
||||
"<extra_id_10>",
|
||||
"<extra_id_11>",
|
||||
"<extra_id_12>",
|
||||
"<extra_id_13>",
|
||||
"<extra_id_14>",
|
||||
"<extra_id_15>",
|
||||
"<extra_id_16>",
|
||||
"<extra_id_17>",
|
||||
"<extra_id_18>",
|
||||
"<extra_id_19>",
|
||||
"<extra_id_20>",
|
||||
"<extra_id_21>",
|
||||
"<extra_id_22>",
|
||||
"<extra_id_23>",
|
||||
"<extra_id_24>",
|
||||
"<extra_id_25>",
|
||||
"<extra_id_26>",
|
||||
"<extra_id_27>",
|
||||
"<extra_id_28>",
|
||||
"<extra_id_29>",
|
||||
"<extra_id_30>",
|
||||
"<extra_id_31>",
|
||||
"<extra_id_32>",
|
||||
"<extra_id_33>",
|
||||
"<extra_id_34>",
|
||||
"<extra_id_35>",
|
||||
"<extra_id_36>",
|
||||
"<extra_id_37>",
|
||||
"<extra_id_38>",
|
||||
"<extra_id_39>",
|
||||
"<extra_id_40>",
|
||||
"<extra_id_41>",
|
||||
"<extra_id_42>",
|
||||
"<extra_id_43>",
|
||||
"<extra_id_44>",
|
||||
"<extra_id_45>",
|
||||
"<extra_id_46>",
|
||||
"<extra_id_47>",
|
||||
"<extra_id_48>",
|
||||
"<extra_id_49>",
|
||||
"<extra_id_50>",
|
||||
"<extra_id_51>",
|
||||
"<extra_id_52>",
|
||||
"<extra_id_53>",
|
||||
"<extra_id_54>",
|
||||
"<extra_id_55>",
|
||||
"<extra_id_56>",
|
||||
"<extra_id_57>",
|
||||
"<extra_id_58>",
|
||||
"<extra_id_59>",
|
||||
"<extra_id_60>",
|
||||
"<extra_id_61>",
|
||||
"<extra_id_62>",
|
||||
"<extra_id_63>",
|
||||
"<extra_id_64>",
|
||||
"<extra_id_65>",
|
||||
"<extra_id_66>",
|
||||
"<extra_id_67>",
|
||||
"<extra_id_68>",
|
||||
"<extra_id_69>",
|
||||
"<extra_id_70>",
|
||||
"<extra_id_71>",
|
||||
"<extra_id_72>",
|
||||
"<extra_id_73>",
|
||||
"<extra_id_74>",
|
||||
"<extra_id_75>",
|
||||
"<extra_id_76>",
|
||||
"<extra_id_77>",
|
||||
"<extra_id_78>",
|
||||
"<extra_id_79>",
|
||||
"<extra_id_80>",
|
||||
"<extra_id_81>",
|
||||
"<extra_id_82>",
|
||||
"<extra_id_83>",
|
||||
"<extra_id_84>",
|
||||
"<extra_id_85>",
|
||||
"<extra_id_86>",
|
||||
"<extra_id_87>",
|
||||
"<extra_id_88>",
|
||||
"<extra_id_89>",
|
||||
"<extra_id_90>",
|
||||
"<extra_id_91>",
|
||||
"<extra_id_92>",
|
||||
"<extra_id_93>",
|
||||
"<extra_id_94>",
|
||||
"<extra_id_95>",
|
||||
"<extra_id_96>",
|
||||
"<extra_id_97>",
|
||||
"<extra_id_98>",
|
||||
"<extra_id_99>",
|
||||
"<extra_id_100>",
|
||||
"<extra_id_101>",
|
||||
"<extra_id_102>",
|
||||
"<extra_id_103>",
|
||||
"<extra_id_104>",
|
||||
"<extra_id_105>",
|
||||
"<extra_id_106>",
|
||||
"<extra_id_107>",
|
||||
"<extra_id_108>",
|
||||
"<extra_id_109>",
|
||||
"<extra_id_110>",
|
||||
"<extra_id_111>",
|
||||
"<extra_id_112>",
|
||||
"<extra_id_113>",
|
||||
"<extra_id_114>",
|
||||
"<extra_id_115>",
|
||||
"<extra_id_116>",
|
||||
"<extra_id_117>",
|
||||
"<extra_id_118>",
|
||||
"<extra_id_119>",
|
||||
"<extra_id_120>",
|
||||
"<extra_id_121>",
|
||||
"<extra_id_122>",
|
||||
"<extra_id_123>",
|
||||
"<extra_id_124>",
|
||||
"<extra_id_125>",
|
||||
"<extra_id_126>",
|
||||
"<extra_id_127>",
|
||||
"<extra_id_128>",
|
||||
"<extra_id_129>",
|
||||
"<extra_id_130>",
|
||||
"<extra_id_131>",
|
||||
"<extra_id_132>",
|
||||
"<extra_id_133>",
|
||||
"<extra_id_134>",
|
||||
"<extra_id_135>",
|
||||
"<extra_id_136>",
|
||||
"<extra_id_137>",
|
||||
"<extra_id_138>",
|
||||
"<extra_id_139>",
|
||||
"<extra_id_140>",
|
||||
"<extra_id_141>",
|
||||
"<extra_id_142>",
|
||||
"<extra_id_143>",
|
||||
"<extra_id_144>",
|
||||
"<extra_id_145>",
|
||||
"<extra_id_146>",
|
||||
"<extra_id_147>",
|
||||
"<extra_id_148>",
|
||||
"<extra_id_149>",
|
||||
"<extra_id_150>",
|
||||
"<extra_id_151>",
|
||||
"<extra_id_152>",
|
||||
"<extra_id_153>",
|
||||
"<extra_id_154>",
|
||||
"<extra_id_155>",
|
||||
"<extra_id_156>",
|
||||
"<extra_id_157>",
|
||||
"<extra_id_158>",
|
||||
"<extra_id_159>",
|
||||
"<extra_id_160>",
|
||||
"<extra_id_161>",
|
||||
"<extra_id_162>",
|
||||
"<extra_id_163>",
|
||||
"<extra_id_164>",
|
||||
"<extra_id_165>",
|
||||
"<extra_id_166>",
|
||||
"<extra_id_167>",
|
||||
"<extra_id_168>",
|
||||
"<extra_id_169>",
|
||||
"<extra_id_170>",
|
||||
"<extra_id_171>",
|
||||
"<extra_id_172>",
|
||||
"<extra_id_173>",
|
||||
"<extra_id_174>",
|
||||
"<extra_id_175>",
|
||||
"<extra_id_176>",
|
||||
"<extra_id_177>",
|
||||
"<extra_id_178>",
|
||||
"<extra_id_179>",
|
||||
"<extra_id_180>",
|
||||
"<extra_id_181>",
|
||||
"<extra_id_182>",
|
||||
"<extra_id_183>",
|
||||
"<extra_id_184>",
|
||||
"<extra_id_185>",
|
||||
"<extra_id_186>",
|
||||
"<extra_id_187>",
|
||||
"<extra_id_188>",
|
||||
"<extra_id_189>",
|
||||
"<extra_id_190>",
|
||||
"<extra_id_191>",
|
||||
"<extra_id_192>",
|
||||
"<extra_id_193>",
|
||||
"<extra_id_194>",
|
||||
"<extra_id_195>",
|
||||
"<extra_id_196>",
|
||||
"<extra_id_197>",
|
||||
"<extra_id_198>",
|
||||
"<extra_id_199>",
|
||||
"<extra_id_200>",
|
||||
"<extra_id_201>",
|
||||
"<extra_id_202>",
|
||||
"<extra_id_203>",
|
||||
"<extra_id_204>",
|
||||
"<extra_id_205>",
|
||||
"<extra_id_206>",
|
||||
"<extra_id_207>",
|
||||
"<extra_id_208>",
|
||||
"<extra_id_209>",
|
||||
"<extra_id_210>",
|
||||
"<extra_id_211>",
|
||||
"<extra_id_212>",
|
||||
"<extra_id_213>",
|
||||
"<extra_id_214>",
|
||||
"<extra_id_215>",
|
||||
"<extra_id_216>",
|
||||
"<extra_id_217>",
|
||||
"<extra_id_218>",
|
||||
"<extra_id_219>",
|
||||
"<extra_id_220>",
|
||||
"<extra_id_221>",
|
||||
"<extra_id_222>",
|
||||
"<extra_id_223>",
|
||||
"<extra_id_224>",
|
||||
"<extra_id_225>",
|
||||
"<extra_id_226>",
|
||||
"<extra_id_227>",
|
||||
"<extra_id_228>",
|
||||
"<extra_id_229>",
|
||||
"<extra_id_230>",
|
||||
"<extra_id_231>",
|
||||
"<extra_id_232>",
|
||||
"<extra_id_233>",
|
||||
"<extra_id_234>",
|
||||
"<extra_id_235>",
|
||||
"<extra_id_236>",
|
||||
"<extra_id_237>",
|
||||
"<extra_id_238>",
|
||||
"<extra_id_239>",
|
||||
"<extra_id_240>",
|
||||
"<extra_id_241>",
|
||||
"<extra_id_242>",
|
||||
"<extra_id_243>",
|
||||
"<extra_id_244>",
|
||||
"<extra_id_245>",
|
||||
"<extra_id_246>",
|
||||
"<extra_id_247>",
|
||||
"<extra_id_248>",
|
||||
"<extra_id_249>",
|
||||
"<extra_id_250>",
|
||||
"<extra_id_251>",
|
||||
"<extra_id_252>",
|
||||
"<extra_id_253>",
|
||||
"<extra_id_254>",
|
||||
"<extra_id_255>",
|
||||
"<extra_id_256>",
|
||||
"<extra_id_257>",
|
||||
"<extra_id_258>",
|
||||
"<extra_id_259>",
|
||||
"<extra_id_260>",
|
||||
"<extra_id_261>",
|
||||
"<extra_id_262>",
|
||||
"<extra_id_263>",
|
||||
"<extra_id_264>",
|
||||
"<extra_id_265>",
|
||||
"<extra_id_266>",
|
||||
"<extra_id_267>",
|
||||
"<extra_id_268>",
|
||||
"<extra_id_269>",
|
||||
"<extra_id_270>",
|
||||
"<extra_id_271>",
|
||||
"<extra_id_272>",
|
||||
"<extra_id_273>",
|
||||
"<extra_id_274>",
|
||||
"<extra_id_275>",
|
||||
"<extra_id_276>",
|
||||
"<extra_id_277>",
|
||||
"<extra_id_278>",
|
||||
"<extra_id_279>",
|
||||
"<extra_id_280>",
|
||||
"<extra_id_281>",
|
||||
"<extra_id_282>",
|
||||
"<extra_id_283>",
|
||||
"<extra_id_284>",
|
||||
"<extra_id_285>",
|
||||
"<extra_id_286>",
|
||||
"<extra_id_287>",
|
||||
"<extra_id_288>",
|
||||
"<extra_id_289>",
|
||||
"<extra_id_290>",
|
||||
"<extra_id_291>",
|
||||
"<extra_id_292>",
|
||||
"<extra_id_293>",
|
||||
"<extra_id_294>",
|
||||
"<extra_id_295>",
|
||||
"<extra_id_296>",
|
||||
"<extra_id_297>",
|
||||
"<extra_id_298>",
|
||||
"<extra_id_299>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "<pad>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
BIN
google/umt5-xxl/spiece.model
(Stored with Git LFS)
Normal file
BIN
google/umt5-xxl/spiece.model
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
google/umt5-xxl/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
google/umt5-xxl/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2748
google/umt5-xxl/tokenizer_config.json
Normal file
2748
google/umt5-xxl/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth
(Stored with Git LFS)
Normal file
BIN
models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
models_t5_umt5-xxl-enc-bf16.pth
(Stored with Git LFS)
Normal file
BIN
models_t5_umt5-xxl-enc-bf16.pth
(Stored with Git LFS)
Normal file
Binary file not shown.
3
relighting_lora.ckpt
Normal file
3
relighting_lora.ckpt
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:49fe0a5a5af97c3f410598ddb146b5f4b3f30b2a526ec8cc32e9f032a1d328f7
|
||||
size 2873429974
|
||||
201
relighting_lora/README.md
Normal file
201
relighting_lora/README.md
Normal file
@ -0,0 +1,201 @@
|
||||
---
|
||||
library_name: peft
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.14.0
|
||||
41
relighting_lora/adapter_config.json
Normal file
41
relighting_lora/adapter_config.json
Normal file
@ -0,0 +1,41 @@
|
||||
{
|
||||
"alpha_pattern": {},
|
||||
"auto_mapping": {
|
||||
"base_model_class": "WanxiangI2VHumanOmniArch",
|
||||
"parent_library": "hfm.archs.wanxiang_i2v.wanxiang_i2v_human_omni_arch"
|
||||
},
|
||||
"base_model_name_or_path": null,
|
||||
"bias": "none",
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": "gaussian",
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.0,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"r": 128,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"ffn.0",
|
||||
"k",
|
||||
"q",
|
||||
"v",
|
||||
"ffn.2",
|
||||
"v_img",
|
||||
"o",
|
||||
"k_img"
|
||||
],
|
||||
"task_type": null,
|
||||
"use_dora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
relighting_lora/adapter_model.safetensors
Normal file
3
relighting_lora/adapter_model.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e821a68a66964c4c00dc8b5d06bfc8cc7e24ab77316c547eb41174097394899c
|
||||
size 2873221376
|
||||
200
xlm-roberta-large/README.md
Normal file
200
xlm-roberta-large/README.md
Normal file
@ -0,0 +1,200 @@
|
||||
---
|
||||
tags:
|
||||
- exbert
|
||||
language:
|
||||
- multilingual
|
||||
- af
|
||||
- am
|
||||
- ar
|
||||
- as
|
||||
- az
|
||||
- be
|
||||
- bg
|
||||
- bn
|
||||
- br
|
||||
- bs
|
||||
- ca
|
||||
- cs
|
||||
- cy
|
||||
- da
|
||||
- de
|
||||
- el
|
||||
- en
|
||||
- eo
|
||||
- es
|
||||
- et
|
||||
- eu
|
||||
- fa
|
||||
- fi
|
||||
- fr
|
||||
- fy
|
||||
- ga
|
||||
- gd
|
||||
- gl
|
||||
- gu
|
||||
- ha
|
||||
- he
|
||||
- hi
|
||||
- hr
|
||||
- hu
|
||||
- hy
|
||||
- id
|
||||
- is
|
||||
- it
|
||||
- ja
|
||||
- jv
|
||||
- ka
|
||||
- kk
|
||||
- km
|
||||
- kn
|
||||
- ko
|
||||
- ku
|
||||
- ky
|
||||
- la
|
||||
- lo
|
||||
- lt
|
||||
- lv
|
||||
- mg
|
||||
- mk
|
||||
- ml
|
||||
- mn
|
||||
- mr
|
||||
- ms
|
||||
- my
|
||||
- ne
|
||||
- nl
|
||||
- no
|
||||
- om
|
||||
- or
|
||||
- pa
|
||||
- pl
|
||||
- ps
|
||||
- pt
|
||||
- ro
|
||||
- ru
|
||||
- sa
|
||||
- sd
|
||||
- si
|
||||
- sk
|
||||
- sl
|
||||
- so
|
||||
- sq
|
||||
- sr
|
||||
- su
|
||||
- sv
|
||||
- sw
|
||||
- ta
|
||||
- te
|
||||
- th
|
||||
- tl
|
||||
- tr
|
||||
- ug
|
||||
- uk
|
||||
- ur
|
||||
- uz
|
||||
- vi
|
||||
- xh
|
||||
- yi
|
||||
- zh
|
||||
license: mit
|
||||
---
|
||||
|
||||
# XLM-RoBERTa (large-sized model)
|
||||
|
||||
XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper [Unsupervised Cross-lingual Representation Learning at Scale](https://arxiv.org/abs/1911.02116) by Conneau et al. and first released in [this repository](https://github.com/pytorch/fairseq/tree/master/examples/xlmr).
|
||||
|
||||
Disclaimer: The team releasing XLM-RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team.
|
||||
|
||||
## Model description
|
||||
|
||||
XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages.
|
||||
|
||||
RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts.
|
||||
|
||||
More precisely, it was pretrained with the Masked language modeling (MLM) objective. Taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.
|
||||
|
||||
This way, the model learns an inner representation of 100 languages that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the XLM-RoBERTa model as inputs.
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
You can use the raw model for masked language modeling, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?search=xlm-roberta) to look for fine-tuned versions on a task that interests you.
|
||||
|
||||
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation, you should look at models like GPT2.
|
||||
|
||||
## Usage
|
||||
|
||||
You can use this model directly with a pipeline for masked language modeling:
|
||||
|
||||
```python
|
||||
>>> from transformers import pipeline
|
||||
>>> unmasker = pipeline('fill-mask', model='xlm-roberta-large')
|
||||
>>> unmasker("Hello I'm a <mask> model.")
|
||||
|
||||
[{'score': 0.10563907772302628,
|
||||
'sequence': "Hello I'm a fashion model.",
|
||||
'token': 54543,
|
||||
'token_str': 'fashion'},
|
||||
{'score': 0.08015287667512894,
|
||||
'sequence': "Hello I'm a new model.",
|
||||
'token': 3525,
|
||||
'token_str': 'new'},
|
||||
{'score': 0.033413201570510864,
|
||||
'sequence': "Hello I'm a model model.",
|
||||
'token': 3299,
|
||||
'token_str': 'model'},
|
||||
{'score': 0.030217764899134636,
|
||||
'sequence': "Hello I'm a French model.",
|
||||
'token': 92265,
|
||||
'token_str': 'French'},
|
||||
{'score': 0.026436051353812218,
|
||||
'sequence': "Hello I'm a sexy model.",
|
||||
'token': 17473,
|
||||
'token_str': 'sexy'}]
|
||||
```
|
||||
|
||||
Here is how to use this model to get the features of a given text in PyTorch:
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForMaskedLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained('xlm-roberta-large')
|
||||
model = AutoModelForMaskedLM.from_pretrained("xlm-roberta-large")
|
||||
|
||||
# prepare input
|
||||
text = "Replace me by any text you'd like."
|
||||
encoded_input = tokenizer(text, return_tensors='pt')
|
||||
|
||||
# forward pass
|
||||
output = model(**encoded_input)
|
||||
```
|
||||
|
||||
### BibTeX entry and citation info
|
||||
|
||||
```bibtex
|
||||
@article{DBLP:journals/corr/abs-1911-02116,
|
||||
author = {Alexis Conneau and
|
||||
Kartikay Khandelwal and
|
||||
Naman Goyal and
|
||||
Vishrav Chaudhary and
|
||||
Guillaume Wenzek and
|
||||
Francisco Guzm{\'{a}}n and
|
||||
Edouard Grave and
|
||||
Myle Ott and
|
||||
Luke Zettlemoyer and
|
||||
Veselin Stoyanov},
|
||||
title = {Unsupervised Cross-lingual Representation Learning at Scale},
|
||||
journal = {CoRR},
|
||||
volume = {abs/1911.02116},
|
||||
year = {2019},
|
||||
url = {http://arxiv.org/abs/1911.02116},
|
||||
eprinttype = {arXiv},
|
||||
eprint = {1911.02116},
|
||||
timestamp = {Mon, 11 Nov 2019 18:38:09 +0100},
|
||||
biburl = {https://dblp.org/rec/journals/corr/abs-1911-02116.bib},
|
||||
bibsource = {dblp computer science bibliography, https://dblp.org}
|
||||
}
|
||||
```
|
||||
|
||||
<a href="https://huggingface.co/exbert/?model=xlm-roberta-base">
|
||||
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
|
||||
</a>
|
||||
25
xlm-roberta-large/config.json
Normal file
25
xlm-roberta-large/config.json
Normal file
@ -0,0 +1,25 @@
|
||||
{
|
||||
"architectures": [
|
||||
"XLMRobertaForMaskedLM"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.1,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 514,
|
||||
"model_type": "xlm-roberta",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"output_past": true,
|
||||
"pad_token_id": 1,
|
||||
"position_embedding_type": "absolute",
|
||||
"transformers_version": "4.17.0.dev0",
|
||||
"type_vocab_size": 1,
|
||||
"use_cache": true,
|
||||
"vocab_size": 250002
|
||||
}
|
||||
1
xlm-roberta-large/configuration.json
Normal file
1
xlm-roberta-large/configuration.json
Normal file
@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "fill-mask", "allow_remote": true}
|
||||
3
xlm-roberta-large/flax_model.msgpack
Normal file
3
xlm-roberta-large/flax_model.msgpack
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:96d19a73ca044be7c23518d2d23154eb0a1e6fb301d3b086e2d80bdfff1391ce
|
||||
size 2240584013
|
||||
3
xlm-roberta-large/model.safetensors
Normal file
3
xlm-roberta-large/model.safetensors
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2dfa19f172412917cab174da04b46e2134811b723666965fd0aabd97caa6e23b
|
||||
size 2244817354
|
||||
27
xlm-roberta-large/onnx/config.json
Normal file
27
xlm-roberta-large/onnx/config.json
Normal file
@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "xlm-roberta-large",
|
||||
"architectures": [
|
||||
"XLMRobertaForMaskedLM"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.1,
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": null,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 514,
|
||||
"model_type": "xlm-roberta",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"output_past": true,
|
||||
"pad_token_id": 1,
|
||||
"position_embedding_type": "absolute",
|
||||
"transformers_version": "4.30.2",
|
||||
"type_vocab_size": 1,
|
||||
"use_cache": true,
|
||||
"vocab_size": 250002
|
||||
}
|
||||
3
xlm-roberta-large/onnx/model.onnx
Normal file
3
xlm-roberta-large/onnx/model.onnx
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bb5a52503a3ef35247f5b5ae6c473aaae60505dd3ffaef56d7b69e2f84683c05
|
||||
size 545850
|
||||
3
xlm-roberta-large/onnx/model.onnx_data
Normal file
3
xlm-roberta-large/onnx/model.onnx_data
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1798dab29db9d3fe4193ffa091512730369bd1c1c2041de430e09394d4f57df1
|
||||
size 2235363328
|
||||
BIN
xlm-roberta-large/onnx/sentencepiece.bpe.model
(Stored with Git LFS)
Normal file
BIN
xlm-roberta-large/onnx/sentencepiece.bpe.model
(Stored with Git LFS)
Normal file
Binary file not shown.
15
xlm-roberta-large/onnx/special_tokens_map.json
Normal file
15
xlm-roberta-large/onnx/special_tokens_map.json
Normal file
@ -0,0 +1,15 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"cls_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"mask_token": {
|
||||
"content": "<mask>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<pad>",
|
||||
"sep_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
BIN
xlm-roberta-large/onnx/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
xlm-roberta-large/onnx/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
19
xlm-roberta-large/onnx/tokenizer_config.json
Normal file
19
xlm-roberta-large/onnx/tokenizer_config.json
Normal file
@ -0,0 +1,19 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"cls_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"mask_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<mask>",
|
||||
"lstrip": true,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"model_max_length": 512,
|
||||
"pad_token": "<pad>",
|
||||
"sep_token": "</s>",
|
||||
"tokenizer_class": "XLMRobertaTokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
3
xlm-roberta-large/pytorch_model.bin
Normal file
3
xlm-roberta-large/pytorch_model.bin
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:01e55aa45dbb9164fee19aef60007a1c91d175051c01be1fb15056cfa60f3e53
|
||||
size 2244861551
|
||||
BIN
xlm-roberta-large/sentencepiece.bpe.model
(Stored with Git LFS)
Normal file
BIN
xlm-roberta-large/sentencepiece.bpe.model
(Stored with Git LFS)
Normal file
Binary file not shown.
3
xlm-roberta-large/tf_model.h5
Normal file
3
xlm-roberta-large/tf_model.h5
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a465c8d459fe83e10db5655221e2e7e7b6df3de2216c524399358d17ac7315ea
|
||||
size 2240076248
|
||||
3
xlm-roberta-large/tokenizer.json
Normal file
3
xlm-roberta-large/tokenizer.json
Normal file
@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a898ea75433890f6610f4e470b8ebeb0c21dce5c8dd61f892eb09eb5919d2e2c
|
||||
size 9096718
|
||||
Reference in New Issue
Block a user