+
+
+
+ +
+ π Wan ο½ π₯οΈ GitHub | π€ Hugging Face | π€ ModelScope | π Paper (Coming soon) | π Blog | π¬ WeChat Group | π Discord
+
+
+-----
+
+[**Wan: Open and Advanced Large-Scale Video Generative Models**]()
+
+
+
+## π₯ Latest News!!
+
+* Feb 25, 2025: π We've released the inference code and weights of Wan2.1.
+
+
+## π Todo List
+- Wan2.1 Text-to-Video
+ - [x] Multi-GPU Inference code of the 14B and 1.3B models
+ - [x] Checkpoints of the 14B and 1.3B models
+ - [x] Gradio demo
+ - [x] Diffusers integration
+ - [ ] ComfyUI integration
+- Wan2.1 Image-to-Video
+ - [x] Multi-GPU Inference code of the 14B model
+ - [x] Checkpoints of the 14B model
+ - [x] Gradio demo
+ - [x] Diffusers integration
+ - [ ] ComfyUI integration
+
+
+## Quickstart
+
+#### Installation
+Clone the repo:
+```
+git clone https://github.com/Wan-Video/Wan2.1.git
+cd Wan2.1
+```
+
+Install dependencies:
+```
+# Ensure torch >= 2.4.0
+pip install -r requirements.txt
+```
+
+
+#### Model Download
+
+| Models | Download Link | Notes |
+| --------------|-------------------------------------------------------------------------------|-------------------------------|
+| T2V-14B | π€ [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B) π€ [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-T2V-14B) | Supports both 480P and 720P
+| I2V-14B-720P | π€ [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P) π€ [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-720P) | Supports 720P
+| I2V-14B-480P | π€ [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P) π€ [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-I2V-14B-480P) | Supports 480P
+| T2V-1.3B | π€ [Huggingface](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B) π€ [ModelScope](https://www.modelscope.cn/models/Wan-AI/Wan2.1-T2V-1.3B) | Supports 480P
+
+> π‘Note: The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution.
+
+
+Download models using π€ huggingface-cli:
+```
+pip install "huggingface_hub[cli]"
+huggingface-cli download Wan-AI/Wan2.1-I2V-14B-720P-Diffusers --local-dir ./Wan2.1-I2V-14B-720P-Diffusers
+```
+
+Download models using π€ modelscope-cli:
+```
+pip install modelscope
+modelscope download Wan-AI/Wan2.1-I2V-14B-720P-Diffusers --local_dir ./Wan2.1-I2V-14B-720P-Diffusers
+```
+
+#### Run Image-to-Video Generation
+
+Similar to Text-to-Video, Image-to-Video is also divided into processes with and without the prompt extension step. The specific parameters and their corresponding settings are as follows:
+
+
+
+
+
+##### (1) Without Prompt Extention
+
+- Single-GPU inference
+```
+python generate.py --task i2v-14B --size 1280*720 --ckpt_dir ./Wan2.1-I2V-14B-720P --image examples/i2v_input.JPG --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
+```
+
+> π‘For the Image-to-Video task, the `size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image.
+
+- Multi-GPU inference using FSDP + xDiT USP
+
+```
+pip install "xfuser>=0.4.1"
+torchrun --nproc_per_node=8 generate.py --task i2v-14B --size 1280*720 --ckpt_dir ./Wan2.1-I2V-14B-720P --image examples/i2v_input.JPG --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
+```
+
+Wan can also be run directly using π€ Diffusers!
+
+```python
+import torch
+import numpy as np
+from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
+from diffusers.utils import export_to_video, load_image
+from transformers import CLIPVisionModel
+
+# Available models: Wan-AI/Wan2.1-I2V-14B-480P-Diffusers, Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+model_id = "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers"
+image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+image = load_image(
+ "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
+)
+max_area = 720 * 1280
+aspect_ratio = image.height / image.width
+mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
+height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
+width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
+image = image.resize((width, height))
+prompt = (
+ "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in "
+ "the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
+)
+negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
+
+output = pipe(
+ image=image, prompt=prompt, negative_prompt=negative_prompt, height=height, width=width, num_frames=81, guidance_scale=5.0
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+```
+
+##### (2) Using Prompt Extention
+
+
+Run with local prompt extention using `Qwen/Qwen2.5-VL-7B-Instruct`:
+```
+python generate.py --task i2v-14B --size 1280*720 --ckpt_dir ./Wan2.1-I2V-14B-720P --image examples/i2v_input.JPG --use_prompt_extend --prompt_extend_model Qwen/Qwen2.5-VL-7B-Instruct --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
+```
+
+Run with remote prompt extention using `dashscope`:
+```
+DASH_API_KEY=your_key python generate.py --task i2v-14B --size 1280*720 --ckpt_dir ./Wan2.1-I2V-14B-720P --image examples/i2v_input.JPG --use_prompt_extend --prompt_extend_method 'dashscope' --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
+```
+
+##### (3) Runing local gradio
+
+```
+cd gradio
+# if one only uses 480P model in gradio
+DASH_API_KEY=your_key python i2v_14B_singleGPU.py --prompt_extend_method 'dashscope' --ckpt_dir_480p ./Wan2.1-I2V-14B-480P
+
+# if one only uses 720P model in gradio
+DASH_API_KEY=your_key python i2v_14B_singleGPU.py --prompt_extend_method 'dashscope' --ckpt_dir_720p ./Wan2.1-I2V-14B-720P
+
+# if one uses both 480P and 720P models in gradio
+DASH_API_KEY=your_key python i2v_14B_singleGPU.py --prompt_extend_method 'dashscope' --ckpt_dir_480p ./Wan2.1-I2V-14B-480P --ckpt_dir_720p ./Wan2.1-I2V-14B-720P
+```
+
+
+## Manual Evaluation
+
+We conducted extensive manual evaluations to evaluate the performance of the Image-to-Video model, and the results are presented in the table below. The results clearly indicate that **Wan2.1** outperforms both closed-source and open-source models.
+
+
+
+ Task
+ Resolution
+ Model
+
+
+
+
+ 480P
+ 720P
+
+
+ i2v-14B
+ β
+ βοΈ
+ Wan2.1-I2V-14B-720P
+
+
+
+i2v-14B
+ βοΈ
+ β
+ Wan2.1-T2V-14B-480P
+
+
+
+
+## Computational Efficiency on Different GPUs
+
+We test the computational efficiency of different **Wan2.1** models on different GPUs in the following table. The results are presented in the format: **Total time (s) / peak GPU memory (GB)**.
+
+
+
+
+
+
+> The parameter settings for the tests presented in this table are as follows:
+> (1) For the 1.3B model on 8 GPUs, set `--ring_size 8` and `--ulysses_size 1`;
+> (2) For the 14B model on 1 GPU, use `--offload_model True`;
+> (3) For the 1.3B model on a single 4090 GPU, set `--offload_model True --t5_cpu`;
+> (4) For all testings, no prompt extension was applied, meaning `--use_prompt_extend` was not enabled.
+
+-------
+
+## Introduction of Wan2.1
+
+**Wan2.1** is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the modelβs performance and versatility.
+
+
+##### (1) 3D Variational Autoencoders
+We propose a novel 3D causal VAE architecture, termed **Wan-VAE** specifically designed for video generation. By combining multiple strategies, we improve spatio-temporal compression, reduce memory usage, and ensure temporal causality. **Wan-VAE** demonstrates significant advantages in performance efficiency compared to other open-source VAEs. Furthermore, our **Wan-VAE** can encode and decode unlimited-length 1080P videos without losing historical temporal information, making it particularly well-suited for video generation tasks.
+
+
+
+
+
+
+
+##### (2) Video Diffusion DiT
+
+**Wan2.1** is designed using the Flow Matching framework within the paradigm of mainstream Diffusion Transformers. Our model's architecture uses the T5 Encoder to encode multilingual text input, with cross-attention in each transformer block embedding the text into the model structure. Additionally, we employ an MLP with a Linear layer and a SiLU layer to process the input time embeddings and predict six modulation parameters individually. This MLP is shared across all transformer blocks, with each block learning a distinct set of biases. Our experimental findings reveal a significant performance improvement with this approach at the same parameter scale.
+
+
+
+
+
+
+| Model | Dimension | Input Dimension | Output Dimension | Feedforward Dimension | Frequency Dimension | Number of Heads | Number of Layers |
+|--------|-----------|-----------------|------------------|-----------------------|---------------------|-----------------|------------------|
+| 1.3B | 1536 | 16 | 16 | 8960 | 256 | 12 | 30 |
+| 14B | 5120 | 16 | 16 | 13824 | 256 | 40 | 40 |
+
+
+
+##### Data
+
+We curated and deduplicated a candidate dataset comprising a vast amount of image and video data. During the data curation process, we designed a four-step data cleaning process, focusing on fundamental dimensions, visual quality and motion quality. Through the robust data processing pipeline, we can easily obtain high-quality, diverse, and large-scale training sets of images and videos.
+
+
+
+
+##### Comparisons to SOTA
+We compared **Wan2.1** with leading open-source and closed-source models to evaluate the performace. Using our carefully designed set of 1,035 internal prompts, we tested across 14 major dimensions and 26 sub-dimensions. We then compute the total score by performing a weighted calculation on the scores of each dimension, utilizing weights derived from human preferences in the matching process. The detailed results are shown in the table below. These results demonstrate our model's superior performance compared to both open-source and closed-source models.
+
+
+
+
+## Citation
+If you find our work helpful, please cite us.
+
+```
+@article{wan2.1,
+ title = {Wan: Open and Advanced Large-Scale Video Generative Models},
+ author = {Wan Team},
+ journal = {},
+ year = {2025}
+}
+```
+
+## License Agreement
+The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generate contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the [license](LICENSE.txt).
+
+
+## Acknowledgements
+
+We would like to thank the contributors to the [SD3](https://huggingface.co/stabilityai/stable-diffusion-3-medium), [Qwen](https://huggingface.co/Qwen), [umt5-xxl](https://huggingface.co/google/umt5-xxl), [diffusers](https://github.com/huggingface/diffusers) and [HuggingFace](https://huggingface.co) repositories, for their open research.
+
+
+
+## Contact Us
+If you would like to leave a message to our research or product teams, feel free to join our [Discord](https://discord.gg/p5XbdQV7) or [WeChat groups](https://gw.alicdn.com/imgextra/i2/O1CN01tqjWFi1ByuyehkTSB_!!6000000000015-0-tps-611-1279.jpg)!
\ No newline at end of file
diff --git a/assets/comp_effic.png b/assets/comp_effic.png
new file mode 100644
index 0000000000000000000000000000000000000000..741f12abd4bc11efd6177e7c59765d87eaf7e395
--- /dev/null
+++ b/assets/comp_effic.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e225caffb4b31295ad150f95ee852e4c3dde4a00ac8f79a2ff500f2ce26b8d
+size 1793594
diff --git a/assets/data_for_diff_stage.jpg b/assets/data_for_diff_stage.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a7ba97f116a3e3304d9960069344019787181368
--- /dev/null
+++ b/assets/data_for_diff_stage.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59aec08409f2d46b0e640e4e120dc7cca52c08c3de56d026602dbcff1ebf241a
+size 528268
diff --git a/assets/i2v_res.png b/assets/i2v_res.png
new file mode 100644
index 0000000000000000000000000000000000000000..98470f121ae318c11d25fd3728cd5c93e0c6993d
--- /dev/null
+++ b/assets/i2v_res.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6823b3206d8d0cb18d3b5b949dec1217f1178109ba11f14e977b67e1f7b8a248
+size 891681
diff --git a/assets/logo.png b/assets/logo.png
new file mode 100644
index 0000000000000000000000000000000000000000..14cea40a9ec4c2aa8de3b46806b25d766980d909
--- /dev/null
+++ b/assets/logo.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96cddc0f667293436d0b9f92a299b6346b65b231d38ee49719a33d46c91fe1e3
+size 56322
diff --git a/assets/t2v_res.jpg b/assets/t2v_res.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7549a1f66d7aa8fb90b6e6181188efc1be0edc28
--- /dev/null
+++ b/assets/t2v_res.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91db579092446be2a834bc67721a8e4346936f38c4edb912f459ca3e10f8f439
+size 301030
diff --git a/assets/vben_1.3b_vs_sota.png b/assets/vben_1.3b_vs_sota.png
new file mode 100644
index 0000000000000000000000000000000000000000..2d14bab7f9fb058a71ce70a78b25afb8d482079f
--- /dev/null
+++ b/assets/vben_1.3b_vs_sota.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7705db79f2e1428ec7a1e6fff8c4fbde062fb95bb233516ddbd04b20007c845
+size 515765
diff --git a/assets/vben_vs_sota.png b/assets/vben_vs_sota.png
new file mode 100644
index 0000000000000000000000000000000000000000..cded47bc519dc2aeae2f370228209e8c9e74bc0b
--- /dev/null
+++ b/assets/vben_vs_sota.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0e86ca85046d2675f97984b88b6e74df07bba8a62a31ab8a1aef50d4eda44e
+size 1552119
diff --git a/assets/video_dit_arch.jpg b/assets/video_dit_arch.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..97d9c19d286b432c33d644d5b00061c2e2a3545a
--- /dev/null
+++ b/assets/video_dit_arch.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:195dceec6570289d8b01cc51d2e28a7786216f19de55b23978a52610d1646a66
+size 643369
diff --git a/assets/video_vae_res.jpg b/assets/video_vae_res.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..91ca92abf061f569b335f3b8ca63e796ce2f6103
--- /dev/null
+++ b/assets/video_vae_res.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f9e7f7353848056a615c8ef35ab86ec22976bb46cb27405008b4089701945c
+size 212586
diff --git a/examples/i2v_input.JPG b/examples/i2v_input.JPG
new file mode 100644
index 0000000000000000000000000000000000000000..8c7fabd943752179587eb717362db32ce1eb4800
--- /dev/null
+++ b/examples/i2v_input.JPG
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077e3d965090c9028c69c00931675f42e1acc815c6eb450ab291b3b72d211a8e
+size 250628
diff --git a/image_encoder/config.json b/image_encoder/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..3be9aa15022880cec03c998d71d0b48ffeff18e2
--- /dev/null
+++ b/image_encoder/config.json
@@ -0,0 +1,23 @@
+{
+ "_name_or_path": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+ "architectures": [
+ "CLIPVisionModelWithProjection"
+ ],
+ "attention_dropout": 0.0,
+ "dropout": 0.0,
+ "hidden_act": "gelu",
+ "hidden_size": 1280,
+ "image_size": 224,
+ "initializer_factor": 1.0,
+ "initializer_range": 0.02,
+ "intermediate_size": 5120,
+ "layer_norm_eps": 1e-05,
+ "model_type": "clip_vision_model",
+ "num_attention_heads": 16,
+ "num_channels": 3,
+ "num_hidden_layers": 32,
+ "patch_size": 14,
+ "projection_dim": 1024,
+ "torch_dtype": "float32",
+ "transformers_version": "4.48.0.dev0"
+}
diff --git a/image_encoder/model.safetensors b/image_encoder/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d546049b3265c1438f03821e610dbb4380402b2f
--- /dev/null
+++ b/image_encoder/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c0bbf4f43f319a80335387d371742333807589c5bb4130a1a2a5d4abf6bf72
+size 1264217760
diff --git a/image_processor/preprocessor_config.json b/image_processor/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ae07b4c27c8e8d50505ee232210ef38d1e1cb2a2
--- /dev/null
+++ b/image_processor/preprocessor_config.json
@@ -0,0 +1,28 @@
+{
+ "crop_size": {
+ "height": 224,
+ "width": 224
+ },
+ "do_center_crop": false,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.48145466,
+ 0.4578275,
+ 0.40821073
+ ],
+ "image_processor_type": "CLIPImageProcessor",
+ "image_std": [
+ 0.26862954,
+ 0.26130258,
+ 0.27577711
+ ],
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "height": 224,
+ "width": 224
+ }
+}
diff --git a/model_index.json b/model_index.json
new file mode 100644
index 0000000000000000000000000000000000000000..b5e23b8a97ed52fa7fef8bdfa5bda52152f74936
--- /dev/null
+++ b/model_index.json
@@ -0,0 +1,32 @@
+{
+ "_class_name": "WanImageToVideoPipeline",
+ "_diffusers_version": "0.33.0.dev0",
+ "image_encoder": [
+ "transformers",
+ "CLIPVisionModelWithProjection"
+ ],
+ "image_processor": [
+ "transformers",
+ "CLIPImageProcessor"
+ ],
+ "scheduler": [
+ "diffusers",
+ "FlowMatchEulerDiscreteScheduler"
+ ],
+ "text_encoder": [
+ "transformers",
+ "UMT5EncoderModel"
+ ],
+ "tokenizer": [
+ "transformers",
+ "T5TokenizerFast"
+ ],
+ "transformer": [
+ "diffusers",
+ "WanTransformer3DModel"
+ ],
+ "vae": [
+ "diffusers",
+ "AutoencoderKLWan"
+ ]
+}
diff --git a/scheduler/scheduler_config.json b/scheduler/scheduler_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..68954ef5992ba98981b93175a67460852fefae00
--- /dev/null
+++ b/scheduler/scheduler_config.json
@@ -0,0 +1,28 @@
+{
+ "_class_name": "UniPCMultistepScheduler",
+ "_diffusers_version": "0.33.0.dev0",
+ "beta_end": 0.02,
+ "beta_schedule": "linear",
+ "beta_start": 0.0001,
+ "disable_corrector": [],
+ "dynamic_thresholding_ratio": 0.995,
+ "final_sigmas_type": "zero",
+ "flow_shift": 5.0,
+ "lower_order_final": true,
+ "num_train_timesteps": 1000,
+ "predict_x0": true,
+ "prediction_type": "flow_prediction",
+ "rescale_betas_zero_snr": false,
+ "sample_max_value": 1.0,
+ "solver_order": 2,
+ "solver_p": null,
+ "solver_type": "bh2",
+ "steps_offset": 0,
+ "thresholding": false,
+ "timestep_spacing": "linspace",
+ "trained_betas": null,
+ "use_beta_sigmas": false,
+ "use_exponential_sigmas": false,
+ "use_flow_sigmas": true,
+ "use_karras_sigmas": false
+}
diff --git a/text_encoder/config.json b/text_encoder/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..2fd01c57dddd8ae386d518c69c087c8ba8c73804
--- /dev/null
+++ b/text_encoder/config.json
@@ -0,0 +1,34 @@
+{
+ "_name_or_path": "google/umt5-xxl",
+ "architectures": [
+ "UMT5EncoderModel"
+ ],
+ "classifier_dropout": 0.0,
+ "d_ff": 10240,
+ "d_kv": 64,
+ "d_model": 4096,
+ "decoder_start_token_id": 0,
+ "dense_act_fn": "gelu_new",
+ "dropout_rate": 0.1,
+ "eos_token_id": 1,
+ "feed_forward_proj": "gated-gelu",
+ "initializer_factor": 1.0,
+ "is_encoder_decoder": true,
+ "is_gated_act": true,
+ "layer_norm_epsilon": 1e-06,
+ "model_type": "umt5",
+ "num_decoder_layers": 24,
+ "num_heads": 64,
+ "num_layers": 24,
+ "output_past": true,
+ "pad_token_id": 0,
+ "relative_attention_max_distance": 128,
+ "relative_attention_num_buckets": 32,
+ "scalable_attention": true,
+ "tie_word_embeddings": false,
+ "tokenizer_class": "T5Tokenizer",
+ "torch_dtype": "float32",
+ "transformers_version": "4.48.0.dev0",
+ "use_cache": true,
+ "vocab_size": 256384
+}
diff --git a/text_encoder/model-00001-of-00005.safetensors b/text_encoder/model-00001-of-00005.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..383f168e1318f0f8d6777b1ba5e88546c1273c46
--- /dev/null
+++ b/text_encoder/model-00001-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ef3a140898e228a3520c9adec60743d2e8e5b3d229651bb37f1a3921919f99
+size 4972389712
diff --git a/text_encoder/model-00002-of-00005.safetensors b/text_encoder/model-00002-of-00005.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..05f1cf9934e3ec7e228b51a93b56875cee468b86
--- /dev/null
+++ b/text_encoder/model-00002-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481c7b2b39771c44df6dd8d13ee12ed072d731b4a650bd092885d4d52db229ad
+size 4899225672
diff --git a/text_encoder/model-00003-of-00005.safetensors b/text_encoder/model-00003-of-00005.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3ea8c93410053a1d42cde624bdf8faf011d329e3
--- /dev/null
+++ b/text_encoder/model-00003-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f93148bcc04052a169e1e49bfcf6125df6cf9bf243cb9c627da75266cf8e35c3
+size 4966309504
diff --git a/text_encoder/model-00004-of-00005.safetensors b/text_encoder/model-00004-of-00005.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9c4d6361dc5ed76d8c129e9c7ad1c64ec7045637
--- /dev/null
+++ b/text_encoder/model-00004-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a451792c739c05bca4606190cc2dd16731411bac03b4cf6aacc5767321f857c9
+size 4999880704
diff --git a/text_encoder/model-00005-of-00005.safetensors b/text_encoder/model-00005-of-00005.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..75aa52c300dafa768721d112ac5a7f11512156ff
--- /dev/null
+++ b/text_encoder/model-00005-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e76e18d224531b8197a46231cb53daf7f2f6ca707130252becf933026ac4eea
+size 2885866152
diff --git a/text_encoder/model.safetensors.index.json b/text_encoder/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..60ece61b46ecb3e6a5b705ea304bc97535317c2a
--- /dev/null
+++ b/text_encoder/model.safetensors.index.json
@@ -0,0 +1,249 @@
+{
+ "metadata": {
+ "total_size": 22723641344
+ },
+ "weight_map": {
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00005.safetensors",
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
+ "encoder.final_layer_norm.weight": "model-00005-of-00005.safetensors",
+ "shared.weight": "model-00001-of-00005.safetensors"
+ }
+}
diff --git a/tokenizer/special_tokens_map.json b/tokenizer/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..2ed25bf989a28d20b5d4b5822fbc24666d12a6f7
--- /dev/null
+++ b/tokenizer/special_tokens_map.json
@@ -0,0 +1,332 @@
+{
+ "additional_special_tokens": [
+ "
+
