Dhanidjulian yoavhacohen commited on
Commit
62da62a
·
0 Parent(s):

Duplicate from Lightricks/LTX-Video-0.9.5

Browse files

Co-authored-by: Yoav HaCohen <yoavhacohen@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ media/ltx-video_example_00001.gif filter=lfs diff=lfs merge=lfs -text
37
+ media/ltx-video_example_00002.gif filter=lfs diff=lfs merge=lfs -text
38
+ media/ltx-video_example_00003.gif filter=lfs diff=lfs merge=lfs -text
39
+ media/ltx-video_example_00004.gif filter=lfs diff=lfs merge=lfs -text
40
+ media/ltx-video_example_00005.gif filter=lfs diff=lfs merge=lfs -text
41
+ media/ltx-video_example_00006.gif filter=lfs diff=lfs merge=lfs -text
42
+ media/ltx-video_example_00007.gif filter=lfs diff=lfs merge=lfs -text
43
+ media/ltx-video_example_00008.gif filter=lfs diff=lfs merge=lfs -text
44
+ media/ltx-video_example_00009.gif filter=lfs diff=lfs merge=lfs -text
45
+ media/ltx-video_example_00010.gif filter=lfs diff=lfs merge=lfs -text
46
+ media/ltx-video_example_00011.gif filter=lfs diff=lfs merge=lfs -text
47
+ media/ltx-video_example_00012.gif filter=lfs diff=lfs merge=lfs -text
48
+ media/ltx-video_example_00013.gif filter=lfs diff=lfs merge=lfs -text
49
+ media/ltx-video_example_00014.gif filter=lfs diff=lfs merge=lfs -text
50
+ media/ltx-video_example_00015.gif filter=lfs diff=lfs merge=lfs -text
51
+ media/ltx-video_example_00016.gif filter=lfs diff=lfs merge=lfs -text
52
+ media/trailer.gif filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - ltx-video
4
+ - image-to-video
5
+ pinned: true
6
+ language:
7
+ - en
8
+ license: other
9
+ pipeline_tag: text-to-video
10
+ library_name: diffusers
11
+ ---
12
+
13
+ # LTX-Video Model Card
14
+ This model card focuses on the model associated with the LTX-Video model, codebase available [here](https://github.com/Lightricks/LTX-Video).
15
+
16
+ LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 30 FPS videos at a 1216×704 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content.
17
+ We provide a model for both text-to-video as well as image+text-to-video usecases
18
+
19
+ <img src="./media/trailer.gif" alt="trailer" width="512">
20
+
21
+
22
+ | | | | |
23
+ |:---:|:---:|:---:|:---:|
24
+ | ![example1](./media/ltx-video_example_00001.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A woman with long brown hair and light skin smiles at another woman...</summary>A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage.</details> | ![example2](./media/ltx-video_example_00002.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A woman walks away from a white Jeep parked on a city street at night...</summary>A woman walks away from a white Jeep parked on a city street at night, then ascends a staircase and knocks on a door. The woman, wearing a dark jacket and jeans, walks away from the Jeep parked on the left side of the street, her back to the camera; she walks at a steady pace, her arms swinging slightly by her sides; the street is dimly lit, with streetlights casting pools of light on the wet pavement; a man in a dark jacket and jeans walks past the Jeep in the opposite direction; the camera follows the woman from behind as she walks up a set of stairs towards a building with a green door; she reaches the top of the stairs and turns left, continuing to walk towards the building; she reaches the door and knocks on it with her right hand; the camera remains stationary, focused on the doorway; the scene is captured in real-life footage.</details> | ![example3](./media/ltx-video_example_00003.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A woman with blonde hair styled up, wearing a black dress...</summary>A woman with blonde hair styled up, wearing a black dress with sequins and pearl earrings, looks down with a sad expression on her face. The camera remains stationary, focused on the woman's face. The lighting is dim, casting soft shadows on her face. The scene appears to be from a movie or TV show.</details> | ![example4](./media/ltx-video_example_00004.gif)<br><details style="max-width: 300px; margin: auto;"><summary>The camera pans over a snow-covered mountain range...</summary>The camera pans over a snow-covered mountain range, revealing a vast expanse of snow-capped peaks and valleys.The mountains are covered in a thick layer of snow, with some areas appearing almost white while others have a slightly darker, almost grayish hue. The peaks are jagged and irregular, with some rising sharply into the sky while others are more rounded. The valleys are deep and narrow, with steep slopes that are also covered in snow. The trees in the foreground are mostly bare, with only a few leaves remaining on their branches. The sky is overcast, with thick clouds obscuring the sun. The overall impression is one of peace and tranquility, with the snow-covered mountains standing as a testament to the power and beauty of nature.</details> |
25
+ | ![example5](./media/ltx-video_example_00005.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A woman with light skin, wearing a blue jacket and a black hat...</summary>A woman with light skin, wearing a blue jacket and a black hat with a veil, looks down and to her right, then back up as she speaks; she has brown hair styled in an updo, light brown eyebrows, and is wearing a white collared shirt under her jacket; the camera remains stationary on her face as she speaks; the background is out of focus, but shows trees and people in period clothing; the scene is captured in real-life footage.</details> | ![example6](./media/ltx-video_example_00006.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A man in a dimly lit room talks on a vintage telephone...</summary>A man in a dimly lit room talks on a vintage telephone, hangs up, and looks down with a sad expression. He holds the black rotary phone to his right ear with his right hand, his left hand holding a rocks glass with amber liquid. He wears a brown suit jacket over a white shirt, and a gold ring on his left ring finger. His short hair is neatly combed, and he has light skin with visible wrinkles around his eyes. The camera remains stationary, focused on his face and upper body. The room is dark, lit only by a warm light source off-screen to the left, casting shadows on the wall behind him. The scene appears to be from a movie.</details> | ![example7](./media/ltx-video_example_00007.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A prison guard unlocks and opens a cell door...</summary>A prison guard unlocks and opens a cell door to reveal a young man sitting at a table with a woman. The guard, wearing a dark blue uniform with a badge on his left chest, unlocks the cell door with a key held in his right hand and pulls it open; he has short brown hair, light skin, and a neutral expression. The young man, wearing a black and white striped shirt, sits at a table covered with a white tablecloth, facing the woman; he has short brown hair, light skin, and a neutral expression. The woman, wearing a dark blue shirt, sits opposite the young man, her face turned towards him; she has short blonde hair and light skin. The camera remains stationary, capturing the scene from a medium distance, positioned slightly to the right of the guard. The room is dimly lit, with a single light fixture illuminating the table and the two figures. The walls are made of large, grey concrete blocks, and a metal door is visible in the background. The scene is captured in real-life footage.</details> | ![example8](./media/ltx-video_example_00008.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A woman with blood on her face and a white tank top...</summary>A woman with blood on her face and a white tank top looks down and to her right, then back up as she speaks. She has dark hair pulled back, light skin, and her face and chest are covered in blood. The camera angle is a close-up, focused on the woman's face and upper torso. The lighting is dim and blue-toned, creating a somber and intense atmosphere. The scene appears to be from a movie or TV show.</details> |
26
+ | ![example9](./media/ltx-video_example_00009.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A man with graying hair, a beard, and a gray shirt...</summary>A man with graying hair, a beard, and a gray shirt looks down and to his right, then turns his head to the left. The camera angle is a close-up, focused on the man's face. The lighting is dim, with a greenish tint. The scene appears to be real-life footage. Step</details> | ![example10](./media/ltx-video_example_00010.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A clear, turquoise river flows through a rocky canyon...</summary>A clear, turquoise river flows through a rocky canyon, cascading over a small waterfall and forming a pool of water at the bottom.The river is the main focus of the scene, with its clear water reflecting the surrounding trees and rocks. The canyon walls are steep and rocky, with some vegetation growing on them. The trees are mostly pine trees, with their green needles contrasting with the brown and gray rocks. The overall tone of the scene is one of peace and tranquility.</details> | ![example11](./media/ltx-video_example_00011.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A man in a suit enters a room and speaks to two women...</summary>A man in a suit enters a room and speaks to two women sitting on a couch. The man, wearing a dark suit with a gold tie, enters the room from the left and walks towards the center of the frame. He has short gray hair, light skin, and a serious expression. He places his right hand on the back of a chair as he approaches the couch. Two women are seated on a light-colored couch in the background. The woman on the left wears a light blue sweater and has short blonde hair. The woman on the right wears a white sweater and has short blonde hair. The camera remains stationary, focusing on the man as he enters the room. The room is brightly lit, with warm tones reflecting off the walls and furniture. The scene appears to be from a film or television show.</details> | ![example12](./media/ltx-video_example_00012.gif)<br><details style="max-width: 300px; margin: auto;"><summary>The waves crash against the jagged rocks of the shoreline...</summary>The waves crash against the jagged rocks of the shoreline, sending spray high into the air.The rocks are a dark gray color, with sharp edges and deep crevices. The water is a clear blue-green, with white foam where the waves break against the rocks. The sky is a light gray, with a few white clouds dotting the horizon.</details> |
27
+ | ![example13](./media/ltx-video_example_00013.gif)<br><details style="max-width: 300px; margin: auto;"><summary>The camera pans across a cityscape of tall buildings...</summary>The camera pans across a cityscape of tall buildings with a circular building in the center. The camera moves from left to right, showing the tops of the buildings and the circular building in the center. The buildings are various shades of gray and white, and the circular building has a green roof. The camera angle is high, looking down at the city. The lighting is bright, with the sun shining from the upper left, casting shadows from the buildings. The scene is computer-generated imagery.</details> | ![example14](./media/ltx-video_example_00014.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A man walks towards a window, looks out, and then turns around...</summary>A man walks towards a window, looks out, and then turns around. He has short, dark hair, dark skin, and is wearing a brown coat over a red and gray scarf. He walks from left to right towards a window, his gaze fixed on something outside. The camera follows him from behind at a medium distance. The room is brightly lit, with white walls and a large window covered by a white curtain. As he approaches the window, he turns his head slightly to the left, then back to the right. He then turns his entire body to the right, facing the window. The camera remains stationary as he stands in front of the window. The scene is captured in real-life footage.</details> | ![example15](./media/ltx-video_example_00015.gif)<br><details style="max-width: 300px; margin: auto;"><summary>Two police officers in dark blue uniforms and matching hats...</summary>Two police officers in dark blue uniforms and matching hats enter a dimly lit room through a doorway on the left side of the frame. The first officer, with short brown hair and a mustache, steps inside first, followed by his partner, who has a shaved head and a goatee. Both officers have serious expressions and maintain a steady pace as they move deeper into the room. The camera remains stationary, capturing them from a slightly low angle as they enter. The room has exposed brick walls and a corrugated metal ceiling, with a barred window visible in the background. The lighting is low-key, casting shadows on the officers' faces and emphasizing the grim atmosphere. The scene appears to be from a film or television show.</details> | ![example16](./media/ltx-video_example_00016.gif)<br><details style="max-width: 300px; margin: auto;"><summary>A woman with short brown hair, wearing a maroon sleeveless top...</summary>A woman with short brown hair, wearing a maroon sleeveless top and a silver necklace, walks through a room while talking, then a woman with pink hair and a white shirt appears in the doorway and yells. The first woman walks from left to right, her expression serious; she has light skin and her eyebrows are slightly furrowed. The second woman stands in the doorway, her mouth open in a yell; she has light skin and her eyes are wide. The room is dimly lit, with a bookshelf visible in the background. The camera follows the first woman as she walks, then cuts to a close-up of the second woman's face. The scene is captured in real-life footage.</details> |
28
+
29
+ # Models
30
+
31
+ | Model | Version | Notes | inference.py config | ComfyUI workflow (Recommended) |
32
+ |--------------------|---------|---------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------|------------------|
33
+ | ltxv-13b | 0.9.7 | Highest quality, requires more VRAM | [ltxv-13b-0.9.7-dev.yaml](https://github.com/Lightricks/LTX-Video/blob/main/configs/ltxv-13b-0.9.7-dev.yaml) | [ltxv-13b-i2v-base.json](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/ltxv-13b-i2v-base.json) |
34
+ | ltxv-13b-fp8 | 0.9.7 | Quantized model | Coming soon | [ltxv-13b-i2v-base-fp8.json](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/ltxv-13b-i2v-base-fp8.json) |
35
+ | ltxv-2b | 0.9.6 | Good quality, lower VRAM requirement than ltxv-13b | [ltxv-2b-0.9.6-dev.yaml](https://github.com/Lightricks/LTX-Video/blob/main/configs/ltxv-2b-0.9.6-dev.yaml) | [ltxvideo-i2v.json](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/low_level/ltxvideo-i2v.json) |
36
+ | ltxv-2b-distilled | 0.9.6 | 15× faster, real-time capable, fewer steps needed, no STG/CFG required | [ltxv-2b-0.9.6-distilled.yaml](https://github.com/Lightricks/LTX-Video/blob/main/configs/ltxv-2b-0.9.6-distilled.yaml) | [ltxvideo-i2v-distilled.json](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/low_level/ltxvideo-i2v-distilled.json) |
37
+
38
+
39
+ ## Model Details
40
+ - **Developed by:** Lightricks
41
+ - **Model type:** Diffusion-based text-to-video and image-to-video generation model
42
+ - **Language(s):** English
43
+
44
+
45
+ ## Usage
46
+
47
+ ### Direct use
48
+ You can use the model for purposes under the license:
49
+ - 2B version 0.9: [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.license.txt)
50
+ - 2B version 0.9.1 [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.1.license.txt)
51
+ - 2B version 0.9.5 [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltx-video-2b-v0.9.5.license.txt)
52
+ - 2B version 0.9.6-dev [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-2b-0.9.6-dev-04-25.license.txt)
53
+ - 2B version 0.9.6-distilled [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-2b-0.9.6-distilled-04-25.license.txt)
54
+ - 13B version 0.9.7-dev [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev.license.txt)
55
+ - 13B version 0.9.7-dev-fp8 [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev-fp8.license.txt)
56
+ - Temporal upscaler version 0.9.7 [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-temporal-upscaler-0.9.7.license.txt)
57
+ - Spatial upscaler version 0.9.7 [license](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-spatial-upscaler-0.9.7.license.txt)
58
+
59
+
60
+ ### General tips:
61
+ * The model works on resolutions that are divisible by 32 and number of frames that are divisible by 8 + 1 (e.g. 257). In case the resolution or number of frames are not divisible by 32 or 8 + 1, the input will be padded with -1 and then cropped to the desired resolution and number of frames.
62
+ * The model works best on resolutions under 720 x 1280 and number of frames below 257.
63
+ * Prompts should be in English. The more elaborate the better. Good prompt looks like `The turquoise waves crash against the dark, jagged rocks of the shore, sending white foam spraying into the air. The scene is dominated by the stark contrast between the bright blue water and the dark, almost black rocks. The water is a clear, turquoise color, and the waves are capped with white foam. The rocks are dark and jagged, and they are covered in patches of green moss. The shore is lined with lush green vegetation, including trees and bushes. In the background, there are rolling hills covered in dense forest. The sky is cloudy, and the light is dim.`
64
+
65
+ ### Online demo
66
+ The model is accessible right away via the following links:
67
+ - [LTX-Studio image-to-video](https://app.ltx.studio/ltx-video)
68
+ - [Fal.ai text-to-video](https://fal.ai/models/fal-ai/ltx-video)
69
+ - [Fal.ai image-to-video](https://fal.ai/models/fal-ai/ltx-video/image-to-video)
70
+ - [Replicate text-to-video and image-to-video](https://replicate.com/lightricks/ltx-video)
71
+
72
+ ### ComfyUI
73
+ To use our model with ComfyUI, please follow the instructions at a dedicated [ComfyUI repo](https://github.com/Lightricks/ComfyUI-LTXVideo/).
74
+
75
+ ### Run locally
76
+
77
+ #### Installation
78
+
79
+ The codebase was tested with Python 3.10.5, CUDA version 12.2, and supports PyTorch >= 2.1.2.
80
+
81
+ ```bash
82
+ git clone https://github.com/Lightricks/LTX-Video.git
83
+ cd LTX-Video
84
+
85
+ # create env
86
+ python -m venv env
87
+ source env/bin/activate
88
+ python -m pip install -e .\[inference-script\]
89
+ ```
90
+
91
+ #### Inference
92
+
93
+ To use our model, please follow the inference code in [inference.py](https://github.com/Lightricks/LTX-Video/blob/main/inference.py):
94
+
95
+ ##### For text-to-video generation:
96
+
97
+ ```bash
98
+ python inference.py --prompt "PROMPT" --height HEIGHT --width WIDTH --num_frames NUM_FRAMES --seed SEED --pipeline_config ltxv-13b-0.9.7-dev.yaml
99
+ ```
100
+
101
+ ##### For image-to-video generation:
102
+
103
+ ```bash
104
+ python inference.py --prompt "PROMPT" --input_image_path IMAGE_PATH --height HEIGHT --width WIDTH --num_frames NUM_FRAMES --seed SEED --pipeline_config ltxv-13b-0.9.7-dev.yaml
105
+ ```
106
+
107
+ ### Diffusers 🧨
108
+
109
+ LTX Video is compatible with the [Diffusers Python library](https://huggingface.co/docs/diffusers/main/en/index). It supports both text-to-video and image-to-video generation.
110
+
111
+ Make sure you install `diffusers` before trying out the examples below.
112
+
113
+ ```bash
114
+ pip install -U git+https://github.com/huggingface/diffusers
115
+ ```
116
+
117
+ Now, you can run the examples below:
118
+
119
+ ```py
120
+ import torch
121
+ from diffusers import LTXPipeline
122
+ from diffusers.utils import export_to_video
123
+
124
+ pipe = LTXPipeline.from_pretrained("Lightricks/LTX-Video", torch_dtype=torch.bfloat16)
125
+ pipe.to("cuda")
126
+
127
+ prompt = "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
128
+ negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
129
+
130
+ video = pipe(
131
+ prompt=prompt,
132
+ negative_prompt=negative_prompt,
133
+ width=704,
134
+ height=480,
135
+ num_frames=161,
136
+ num_inference_steps=50,
137
+ ).frames[0]
138
+ export_to_video(video, "output.mp4", fps=24)
139
+ ```
140
+
141
+ For image-to-video:
142
+
143
+ ```py
144
+ import torch
145
+ from diffusers import LTXImageToVideoPipeline
146
+ from diffusers.utils import export_to_video, load_image
147
+
148
+ pipe = LTXImageToVideoPipeline.from_pretrained("Lightricks/LTX-Video", torch_dtype=torch.bfloat16)
149
+ pipe.to("cuda")
150
+
151
+ image = load_image(
152
+ "https://huggingface.co/datasets/a-r-r-o-w/tiny-meme-dataset-captioned/resolve/main/images/8.png"
153
+ )
154
+ prompt = "A young girl stands calmly in the foreground, looking directly at the camera, as a house fire rages in the background. Flames engulf the structure, with smoke billowing into the air. Firefighters in protective gear rush to the scene, a fire truck labeled '38' visible behind them. The girl's neutral expression contrasts sharply with the chaos of the fire, creating a poignant and emotionally charged scene."
155
+ negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
156
+
157
+ video = pipe(
158
+ image=image,
159
+ prompt=prompt,
160
+ negative_prompt=negative_prompt,
161
+ width=704,
162
+ height=480,
163
+ num_frames=161,
164
+ num_inference_steps=50,
165
+ ).frames[0]
166
+ export_to_video(video, "output.mp4", fps=24)
167
+ ```
168
+
169
+ To learn more, check out the [official documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video).
170
+
171
+ Diffusers also supports directly loading from the original LTX checkpoints using the `from_single_file()` method. Check out [this section](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video#loading-single-files) to learn more.
172
+
173
+ ## Limitations
174
+ - This model is not intended or able to provide factual information.
175
+ - As a statistical model this checkpoint might amplify existing societal biases.
176
+ - The model may fail to generate videos that matches the prompts perfectly.
177
+ - Prompt following is heavily influenced by the prompting-style.
ltx-video-2b-v0.9.5.license.txt ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ LTX Video 2B 0.9.5 (�LTXV�)
2
+ By Lightricks Ltd. (�Lightricks�)
3
+ Open RAIL-M License
4
+ dated March 5, 2025
5
+
6
+ Section I: PREAMBLE
7
+ Multimodal generative models are being widely adopted and used, and have the potential to transform the way artists, among other individuals, conceive and benefit from artificial intelligence (�AI�) or ML technologies as a tool for content creation. Notwithstanding the current and potential benefits that these artifacts can bring to society at large, there are also concerns about potential misuses of them, either due to their technical limitations or ethical considerations.
8
+ The development and use of AI does not come without concerns. The world has witnessed how AI techniques may, in some instances, become risky for the public in general. These risks come in many forms, from racial discrimination to the misuse of sensitive information.
9
+ This Open RAIL-M License is generally applicable to any machine-learning Model (as defined below). While this License (as defined below) allows commercia use of the Model, the �RAIL� nomenclature indicates that there are use restrictions prohibiting the use of the Model. These restrictions are intended to avoid potential misuse by not permitting the use of the Model in very specific scenarios, in order for the Licensor to be able to enforce the license in case a potential misuse of the Model may occur. Even though derivative versions of the Model could be released under different licensing terms, the License (as defined below) specifies that the use restrictions in the original License must apply to such derivative versions. Lightricks believes in the intersection between open and responsible AI development; thus, this License aims to strike a balance between both in order to enable responsible open-science in the field of AI. This License governs the use of the Model (and its derivatives) and is informed by the model card associated with the Model.
10
+
11
+ NOW THEREFORE, You and Licensor agree as follows:
12
+ 1. Definitions
13
+ 1.1. �Complementary Material� means the accompanying source code and scripts used to define, run, load, benchmark or evaluate the Model, and used to prepare data for training or evaluation, if any. This includes any accompanying documentation, tutorials, examples, etc., if any.
14
+ 1.2. �Contribution� means any work of authorship, including the original version of the Model and any modifications or additions to that Model or Derivatives of the Model thereof, that is intentionally submitted to Licensor for inclusion in the Model by the copyright owner or by an individual or legal entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, �submitted� means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Model, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as �Not a Contribution�.
15
+ 1.3. �Contributor� means Licensor and any individual or legal entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Model.
16
+ 1.4. �Data� means a collection of information and/or content extracted from the dataset used with the Model, including to train, pretrain, or otherwise evaluate the Model. The Data is not licensed under this License.
17
+ 1.5. �Derivatives of the Model� means all modifications to the Model, works based on the Model, or any other model which is created or initialized by transfer of patterns of the weights, parameters, activations or output of the Model, to the other model, in order to cause the other model to perform similarly to the Model, including h � but not limited to - distillation methods entailing the use of intermediate data representations or methods based on the generation of synthetic data by the Model for training the other model.
18
+ 1.6. �Distribution� means any transmission, reproduction, publication or other sharing of the Model or Derivatives of the Model to a third party, including providing the Model as a hosted service made available by electronic or other remote means - e.g. API-based or web access.
19
+ 1.7. �Harm� includes but is not limited to physical, mental, psychological, financial and reputational damage, pain, or loss.
20
+ 1.8. �License� means the terms and conditions for use, reproduction, and Distribution as defined in this document.
21
+ 1.9. �Licensor� means the copyright owner or entity authorized by the copyright owner that is granting the License, including the persons or entities that may have rights in the Model and/or distributing the Model. For the purposes of this License, the Licensor is Lightricks Ltd.
22
+ 1.10. �Model� means any accompanying machine-learning based assemblies (including checkpoints), consisting of learnt weights, parameters (including optimizer states), corresponding to the Lightricks� Model �LTX Video 2B 0.9.5� model architecture as embodied in the Complementary Material, that have been trained or tuned, in whole or in part on the Data, using the Complementary Material.
23
+ 1.11. �Output� means the results of operating a Model as embodied in informational content resulting therefrom.
24
+ 1.12. �Third Parties� means individuals or legal entities that are not under common control with Licensor or You.
25
+ 1.13. �You� (or �Your�) means an individual or legal entity exercising permissions granted by this License and/or making use of the Model for whichever purpose and in any field of use, including usage of the Model in an end-use application - e.g. chatbot, translator, image generator.
26
+
27
+ Section II: INTELLECTUAL PROPERTY RIGHTS
28
+ Both copyright and patent grants apply to the Model, Derivatives of the Model and Complementary Material. The Model and Derivatives of the Model are subject to additional terms as described in Section III, which shall govern the use of the Model and Derivatives of the Model even in the event Section II is held unenforceable.
29
+ 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare, publicly display, publicly perform, sublicense, and distribute the Complementary Material, the Model, and Derivatives of the Model.
30
+ 3. Grant of Patent License. Subject to the terms and conditions of this License and where and as applicable, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this paragraph) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Model and the Complementary Material, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Model to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Model and/or Complementary Material or a Contribution incorporated within the Model and/or Complementary Material constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for the Model and/or Complementary Materials shall terminate as of the date such litigation is asserted or filed.
31
+
32
+ Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
33
+ 4. Distribution and Redistribution. You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model thereof in any medium, with or without modifications, provided that You meet the following conditions:
34
+ 4.1. Use-based restrictions as referenced in paragraph 5 MUST be included as an enforceable provision by You in any type of legal agreement (e.g. a license) governing the use and/or distribution of the Model or Derivatives of the Model, and You shall give notice to subsequent users You Distribute to, that the Model or Derivatives of the Model are subject to paragraph 5. This provision does not apply to the use of Complementary Material.
35
+ 4.2. You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License;
36
+ 4.3. You must cause any modified files to carry prominent notices stating that You changed the files;
37
+ 4.4. You must retain all copyright, patent, trademark, and attribution notices excluding those notices that do not pertain to any part of the Model, Derivatives of the Model.
38
+ You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions - respecting paragraph 4.1 - for use, reproduction, or Distribution of Your modifications, or for any such Derivatives of the Model as a whole, provided Your use, reproduction, and Distribution of the Model otherwise complies with the conditions stated in this License.
39
+ 5. Use-based restrictions. The restrictions set forth in Attachment A are considered Use-based restrictions. Therefore, You cannot use the Model and the Derivatives of the Model in violation of the specified restricted uses. You may use the Model subject to this License, including only for lawful purposes and in accordance with the License. �Use� may include creating any content with, fine-tuning, updating, running, training, evaluating and/or re-parametrizing the Model. You shall require all of Your users who use the Model or a Derivative of the Model to comply with the terms of this paragraph 5.�
40
+ 6. The Output You Generate. Except as set forth herein, Licensor claims no rights in the Output You generate using the Model. You are accountable for input you insert into the Model, the Output you generate and its subsequent uses. No use of the Output can contravene any provision as stated in the License.
41
+
42
+ Section IV: OTHER PROVISIONS
43
+ 7. Updates and Runtime Restrictions. To the maximum extent permitted by law, Licensor reserves the right to restrict (remotely or otherwise) usage of the Model in violation of this License, update the Model through electronic means, or modify the Output of the Model based on updates. You shall undertake reasonable efforts to use the latest version of the Model. Any use of the non-current version of the Model is done solely at your risk.
44
+ 8. Trademarks and related. Nothing in this License permits You to make use of Licensor�s trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between the parties; and any rights not expressly granted herein are reserved by the Licensor.
45
+ 9. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Model and the Complementary Material (and each Contributor provides its Contributions) on an �AS IS� BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Model, Derivatives of the Model, and the Complementary Material and assume any risks associated with Your exercise of permissions under this License.
46
+ 10. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Model and the Complementary Material (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
47
+ 11. Accepting Warranty or Additional Liability. While redistributing the Model, Derivatives of the Model and the Complementary Material thereof, You may choose to offer and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against such Contributor, by reason of your accepting any such warranty or additional liability.
48
+ 12. If any provision of this License is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
49
+ END OF TERMS AND CONDITIONS
50
+
51
+
52
+ Attachment A
53
+ Use Restrictions
54
+ You agree not to use the Model or its Derivatives in any of the following ways:
55
+ (a) Outside of the Permitted Purpose;
56
+ (a) In any way that violates any applicable national, federal, state, local or international law or regulation;
57
+ (b) For the purpose of exploiting, Harming or attempting to exploit or Harm minors in any way;
58
+ (c) To generate or disseminate false information and/or content with the purpose of Harming others;
59
+ (d) To generate or disseminate personal identifiable information that can be used to Harm an individual;
60
+ (e) To generate or disseminate information and/or content (e.g. images, code, posts, articles), and place the information and/or content in any context (e.g. bot generating tweets) without expressly and intelligibly disclaiming that the information and/or content is machine generated;
61
+ (f) To defame, disparage or otherwise harass others;
62
+ (g) To impersonate or attempt to impersonate (e.g. deepfakes) others without their consent;
63
+ (h) For fully automated decision making that adversely impacts an individual�s legal rights or otherwise creates or modifies a binding, enforceable obligation;
64
+ (i) For any use intended to or which has the effect of discriminating against or Harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
65
+ (j) To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological Harm;
66
+ (k) For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
67
+ (l) To provide medical advice and medical results interpretation;
68
+ (m) To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use);
69
+ (n) To generate and/or disseminate malware (including � but not limited to � ransomware) or any other content to be used for the purpose of harming electronic systems;
70
+ (o) To engage in, promote, incite, or facilitate discrimination or other unlawful of harmful conduct in the provision of employment, employment benefits, credit, housing, or other essential goods and services;
71
+ (p) To engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals.
media/ltx-video_example_00001.gif ADDED

Git LFS Details

  • SHA256: b679f14a09d2321b7e34b3ecd23bc01c2cfa75c8d4214a1e59af09826003e2ec
  • Pointer size: 132 Bytes
  • Size of remote file: 7.96 MB
media/ltx-video_example_00002.gif ADDED

Git LFS Details

  • SHA256: 336f4baec79c1bd754c7c1bf3ac0792910cc85b6a3bde15fabeb0fb0f33299ff
  • Pointer size: 132 Bytes
  • Size of remote file: 7.9 MB
media/ltx-video_example_00003.gif ADDED

Git LFS Details

  • SHA256: ab2cb063b872d487fbbab821de7fe8157e7f87af03bd780d55116cb98fc8fc45
  • Pointer size: 132 Bytes
  • Size of remote file: 4.43 MB
media/ltx-video_example_00004.gif ADDED

Git LFS Details

  • SHA256: 0a599a641cc3367fab5a6dd75fc89be63208cc708a1173b2ce7bfeac7208f831
  • Pointer size: 132 Bytes
  • Size of remote file: 6.71 MB
media/ltx-video_example_00005.gif ADDED

Git LFS Details

  • SHA256: 87fdb9556c1218db4b929994e9b807d1d63f4676defef5b418a4edb1ddaa8422
  • Pointer size: 132 Bytes
  • Size of remote file: 5.73 MB
media/ltx-video_example_00006.gif ADDED

Git LFS Details

  • SHA256: f56f3dcc84a871ab4ef1510120f7a4586c7044c5609a897d8177ae8d52eb3eae
  • Pointer size: 132 Bytes
  • Size of remote file: 4.24 MB
media/ltx-video_example_00007.gif ADDED

Git LFS Details

  • SHA256: a08a06681334856db516e969a9ae4290acfd7550f7b970331e87d0223e282bcc
  • Pointer size: 132 Bytes
  • Size of remote file: 7.83 MB
media/ltx-video_example_00008.gif ADDED

Git LFS Details

  • SHA256: 3242c65e11a40177c91b48d8ee18084dc4f907ffe5f11217c5f3e5aa2ca3fe36
  • Pointer size: 132 Bytes
  • Size of remote file: 6.23 MB
media/ltx-video_example_00009.gif ADDED

Git LFS Details

  • SHA256: aa1e0a2ba75c6bda530a798e8aaeb3edc19413970b99d2a67b79839cd14f2fe5
  • Pointer size: 132 Bytes
  • Size of remote file: 6.39 MB
media/ltx-video_example_00010.gif ADDED

Git LFS Details

  • SHA256: bcf1e084e936a75eaae73a29f60935c469b1fc34eb3f5ad89483e88b3a2eaffe
  • Pointer size: 132 Bytes
  • Size of remote file: 6.19 MB
media/ltx-video_example_00011.gif ADDED

Git LFS Details

  • SHA256: 3e3d04f5763ecb416b3b80c3488e48c49991d80661c94e8f08dddd7b890b1b75
  • Pointer size: 132 Bytes
  • Size of remote file: 5.35 MB
media/ltx-video_example_00012.gif ADDED

Git LFS Details

  • SHA256: 39790832fd9bff62c99a799eb4843cf99c9ab73c3f181656acbbd0d4ebf7f471
  • Pointer size: 132 Bytes
  • Size of remote file: 7.47 MB
media/ltx-video_example_00013.gif ADDED

Git LFS Details

  • SHA256: aa7eb790b43f8a55c01d1fbed4c7a7f657fb2ca78a9685833cf9cb558d2002c1
  • Pointer size: 132 Bytes
  • Size of remote file: 9.02 MB
media/ltx-video_example_00014.gif ADDED

Git LFS Details

  • SHA256: 4f7afc4b498a927dcc4e1492548db5c32fa76d117e0410d11e1e0b1929153e54
  • Pointer size: 132 Bytes
  • Size of remote file: 7.43 MB
media/ltx-video_example_00015.gif ADDED

Git LFS Details

  • SHA256: d897c9656e0cba89512ab9d2cbe2d2c0f2ddf907dcab5f7eadab4b96b1cb1efe
  • Pointer size: 132 Bytes
  • Size of remote file: 6.56 MB
media/ltx-video_example_00016.gif ADDED

Git LFS Details

  • SHA256: c74f35e37bba01817ca4ac01dd9195863100eb83e7cb73bbea2b53e0f69a8628
  • Pointer size: 132 Bytes
  • Size of remote file: 7.41 MB
media/trailer.gif ADDED

Git LFS Details

  • SHA256: fe193ca2f5d61ff2c2707efd22c1e76517f7f070896ceec58c9bec0738c6599c
  • Pointer size: 134 Bytes
  • Size of remote file: 147 MB
model_index.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTXPipeline",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "scheduler": [
5
+ "diffusers",
6
+ "FlowMatchEulerDiscreteScheduler"
7
+ ],
8
+ "text_encoder": [
9
+ "transformers",
10
+ "T5EncoderModel"
11
+ ],
12
+ "tokenizer": [
13
+ "transformers",
14
+ "T5Tokenizer"
15
+ ],
16
+ "transformer": [
17
+ "diffusers",
18
+ "LTXVideoTransformer3DModel"
19
+ ],
20
+ "vae": [
21
+ "diffusers",
22
+ "AutoencoderKLLTXVideo"
23
+ ]
24
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 4096,
8
+ "max_shift": 1.15,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": null,
12
+ "time_shift_type": "exponential",
13
+ "use_beta_sigmas": false,
14
+ "use_dynamic_shifting": false,
15
+ "use_exponential_sigmas": false,
16
+ "use_karras_sigmas": false
17
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/t5-v1_1-xxl",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.48.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 32128
32
+ }
text_encoder/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686
3
+ size 4989319680
text_encoder/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ed6556d7507e38af5b428c605fb2a6f2bdb7e80bd481308b865f7a40c551ca
3
+ size 4999830656
text_encoder/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c831635f83041f83faf0024b39c6ecb21b45d70dd38a63ea5bac6c7c6e5e558c
3
+ size 4865612720
text_encoder/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a5f2d69205be92ad48fe5d712d38c2ff55627969116aeffc58bd75a28da468
3
+ size 4194506688
text_encoder/model.safetensors.index.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 19049242624
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00004.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
160
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
161
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
162
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
163
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
164
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
165
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
166
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
167
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
168
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
169
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
170
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
171
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
172
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
173
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
174
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
175
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
176
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
177
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
178
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
179
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
180
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
181
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
182
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
183
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
184
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
185
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
186
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
187
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
188
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
189
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
190
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
191
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
192
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
193
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
194
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
195
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
196
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
197
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
198
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
199
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
200
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
201
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
202
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
203
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
204
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
205
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
206
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
207
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
208
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
209
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
210
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
211
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
212
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
213
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
214
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
215
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
216
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
217
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
218
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
219
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
220
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
221
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
222
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
223
+ "encoder.final_layer_norm.weight": "model-00004-of-00004.safetensors",
224
+ "shared.weight": "model-00001-of-00004.safetensors"
225
+ }
226
+ }
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
tokenizer/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": true,
31
+ "normalized": false,
32
+ "rstrip": true,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": true,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": true,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": true,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": true,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": true,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": true,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": true,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": true,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": true,
119
+ "normalized": false,
120
+ "rstrip": true,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": true,
127
+ "normalized": false,
128
+ "rstrip": true,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": true,
135
+ "normalized": false,
136
+ "rstrip": true,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": true,
143
+ "normalized": false,
144
+ "rstrip": true,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": true,
151
+ "normalized": false,
152
+ "rstrip": true,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": true,
159
+ "normalized": false,
160
+ "rstrip": true,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": true,
167
+ "normalized": false,
168
+ "rstrip": true,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": true,
175
+ "normalized": false,
176
+ "rstrip": true,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": true,
183
+ "normalized": false,
184
+ "rstrip": true,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": true,
191
+ "normalized": false,
192
+ "rstrip": true,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": true,
199
+ "normalized": false,
200
+ "rstrip": true,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": true,
207
+ "normalized": false,
208
+ "rstrip": true,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": true,
215
+ "normalized": false,
216
+ "rstrip": true,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": true,
223
+ "normalized": false,
224
+ "rstrip": true,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": true,
231
+ "normalized": false,
232
+ "rstrip": true,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": true,
239
+ "normalized": false,
240
+ "rstrip": true,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": true,
247
+ "normalized": false,
248
+ "rstrip": true,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": true,
255
+ "normalized": false,
256
+ "rstrip": true,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": true,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": true,
271
+ "normalized": false,
272
+ "rstrip": true,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": true,
279
+ "normalized": false,
280
+ "rstrip": true,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": true,
287
+ "normalized": false,
288
+ "rstrip": true,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": true,
295
+ "normalized": false,
296
+ "rstrip": true,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": true,
303
+ "normalized": false,
304
+ "rstrip": true,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": true,
311
+ "normalized": false,
312
+ "rstrip": true,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": true,
319
+ "normalized": false,
320
+ "rstrip": true,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": true,
327
+ "normalized": false,
328
+ "rstrip": true,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": true,
335
+ "normalized": false,
336
+ "rstrip": true,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": true,
343
+ "normalized": false,
344
+ "rstrip": true,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": true,
351
+ "normalized": false,
352
+ "rstrip": true,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": true,
359
+ "normalized": false,
360
+ "rstrip": true,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": true,
367
+ "normalized": false,
368
+ "rstrip": true,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": true,
375
+ "normalized": false,
376
+ "rstrip": true,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": true,
383
+ "normalized": false,
384
+ "rstrip": true,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": true,
391
+ "normalized": false,
392
+ "rstrip": true,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": true,
399
+ "normalized": false,
400
+ "rstrip": true,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": true,
407
+ "normalized": false,
408
+ "rstrip": true,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": true,
415
+ "normalized": false,
416
+ "rstrip": true,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": true,
423
+ "normalized": false,
424
+ "rstrip": true,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": true,
431
+ "normalized": false,
432
+ "rstrip": true,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": true,
439
+ "normalized": false,
440
+ "rstrip": true,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": true,
447
+ "normalized": false,
448
+ "rstrip": true,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": true,
455
+ "normalized": false,
456
+ "rstrip": true,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": true,
463
+ "normalized": false,
464
+ "rstrip": true,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": true,
471
+ "normalized": false,
472
+ "rstrip": true,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": true,
479
+ "normalized": false,
480
+ "rstrip": true,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": true,
487
+ "normalized": false,
488
+ "rstrip": true,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": true,
495
+ "normalized": false,
496
+ "rstrip": true,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": true,
503
+ "normalized": false,
504
+ "rstrip": true,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": true,
511
+ "normalized": false,
512
+ "rstrip": true,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": true,
519
+ "normalized": false,
520
+ "rstrip": true,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": true,
527
+ "normalized": false,
528
+ "rstrip": true,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": true,
535
+ "normalized": false,
536
+ "rstrip": true,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": true,
543
+ "normalized": false,
544
+ "rstrip": true,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": true,
551
+ "normalized": false,
552
+ "rstrip": true,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": true,
559
+ "normalized": false,
560
+ "rstrip": true,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": true,
567
+ "normalized": false,
568
+ "rstrip": true,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": true,
575
+ "normalized": false,
576
+ "rstrip": true,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": true,
583
+ "normalized": false,
584
+ "rstrip": true,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": true,
591
+ "normalized": false,
592
+ "rstrip": true,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": true,
599
+ "normalized": false,
600
+ "rstrip": true,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": true,
607
+ "normalized": false,
608
+ "rstrip": true,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": true,
615
+ "normalized": false,
616
+ "rstrip": true,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": true,
623
+ "normalized": false,
624
+ "rstrip": true,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": true,
631
+ "normalized": false,
632
+ "rstrip": true,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": true,
639
+ "normalized": false,
640
+ "rstrip": true,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": true,
647
+ "normalized": false,
648
+ "rstrip": true,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": true,
655
+ "normalized": false,
656
+ "rstrip": true,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": true,
663
+ "normalized": false,
664
+ "rstrip": true,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": true,
671
+ "normalized": false,
672
+ "rstrip": true,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": true,
679
+ "normalized": false,
680
+ "rstrip": true,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": true,
687
+ "normalized": false,
688
+ "rstrip": true,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": true,
695
+ "normalized": false,
696
+ "rstrip": true,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": true,
703
+ "normalized": false,
704
+ "rstrip": true,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": true,
711
+ "normalized": false,
712
+ "rstrip": true,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": true,
719
+ "normalized": false,
720
+ "rstrip": true,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": true,
727
+ "normalized": false,
728
+ "rstrip": true,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": true,
735
+ "normalized": false,
736
+ "rstrip": true,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": true,
743
+ "normalized": false,
744
+ "rstrip": true,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": true,
751
+ "normalized": false,
752
+ "rstrip": true,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": true,
759
+ "normalized": false,
760
+ "rstrip": true,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": true,
767
+ "normalized": false,
768
+ "rstrip": true,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": true,
775
+ "normalized": false,
776
+ "rstrip": true,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": true,
783
+ "normalized": false,
784
+ "rstrip": true,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": true,
791
+ "normalized": false,
792
+ "rstrip": true,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": true,
799
+ "normalized": false,
800
+ "rstrip": true,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": true,
807
+ "normalized": false,
808
+ "rstrip": true,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": true,
815
+ "normalized": false,
816
+ "rstrip": true,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": true,
823
+ "normalized": false,
824
+ "rstrip": true,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 128,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
transformer/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTXVideoTransformer3DModel",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "activation_fn": "gelu-approximate",
5
+ "attention_bias": true,
6
+ "attention_head_dim": 64,
7
+ "attention_out_bias": true,
8
+ "caption_channels": 4096,
9
+ "cross_attention_dim": 2048,
10
+ "in_channels": 128,
11
+ "norm_elementwise_affine": false,
12
+ "norm_eps": 1e-06,
13
+ "num_attention_heads": 32,
14
+ "num_layers": 28,
15
+ "out_channels": 128,
16
+ "patch_size": 1,
17
+ "patch_size_t": 1,
18
+ "qk_norm": "rms_norm_across_heads"
19
+ }
transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ccc1b4c4e85ba6881072ed3f26c8d94fe046fe99b2df7c462ce421abfe331f
3
+ size 3846852608
vae/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTXVideo",
3
+ "_diffusers_version": "0.33.0.dev0",
4
+ "block_out_channels": [
5
+ 128,
6
+ 256,
7
+ 512,
8
+ 1024,
9
+ 2048
10
+ ],
11
+ "decoder_block_out_channels": [
12
+ 256,
13
+ 512,
14
+ 1024
15
+ ],
16
+ "decoder_causal": false,
17
+ "decoder_inject_noise": [
18
+ false,
19
+ false,
20
+ false,
21
+ false
22
+ ],
23
+ "decoder_layers_per_block": [
24
+ 5,
25
+ 5,
26
+ 5,
27
+ 5
28
+ ],
29
+ "decoder_spatio_temporal_scaling": [
30
+ true,
31
+ true,
32
+ true
33
+ ],
34
+ "down_block_types": [
35
+ "LTXVideo095DownBlock3D",
36
+ "LTXVideo095DownBlock3D",
37
+ "LTXVideo095DownBlock3D",
38
+ "LTXVideo095DownBlock3D"
39
+ ],
40
+ "downsample_type": [
41
+ "spatial",
42
+ "temporal",
43
+ "spatiotemporal",
44
+ "spatiotemporal"
45
+ ],
46
+ "encoder_causal": true,
47
+ "in_channels": 3,
48
+ "latent_channels": 128,
49
+ "layers_per_block": [
50
+ 4,
51
+ 6,
52
+ 6,
53
+ 2,
54
+ 2
55
+ ],
56
+ "out_channels": 3,
57
+ "patch_size": 4,
58
+ "patch_size_t": 1,
59
+ "resnet_norm_eps": 1e-06,
60
+ "scaling_factor": 1.0,
61
+ "spatial_compression_ratio": 32,
62
+ "spatio_temporal_scaling": [
63
+ true,
64
+ true,
65
+ true,
66
+ true
67
+ ],
68
+ "temporal_compression_ratio": 8,
69
+ "timestep_conditioning": true,
70
+ "upsample_factor": [
71
+ 2,
72
+ 2,
73
+ 2
74
+ ],
75
+ "upsample_residual": [
76
+ true,
77
+ true,
78
+ true
79
+ ]
80
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb65b16cf8ddfd70ccb1c541384ae49ffd6639d754c6b713a11cb72d097233f
3
+ size 2493855612