Commit
·
242e209
verified
·
0
Parent(s):
Duplicate from starvector/starvector-1b-im2svg
Browse filesCo-authored-by: Juan A. Rodriguez <[email protected]>
- .gitattributes +35 -0
- README.md +151 -0
- added_tokens.json +6 -0
- config.json +34 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +591 -0
- preprocessor_config.json +14 -0
- processing_starvector.py +77 -0
- processor_config.json +14 -0
- special_tokens_map.json +51 -0
- starvector_arch.py +204 -0
- tokenizer.json +0 -0
- tokenizer_config.json +222 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
README.md
ADDED
|
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Model Card for StarVector
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
|
| 16 |
+
### Model Description
|
| 17 |
+
|
| 18 |
+
This is the model card for the StarVector model, a 🤗 transformers model. StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.
|
| 19 |
+
|
| 20 |
+
- **Developed by:** ServiceNow Research, Mila - Quebec AI Institute, ETS, Montreal.
|
| 21 |
+
- **Shared by :** Juan A Rodriguez, Abhay Puri, Shubham Agarwal, Issam H. Laradji, Sai Rajeswar, Pau Rodriguez, David Vazquez, Christopher Pal, Marco Pedersoli.
|
| 22 |
+
- **Model type:** Vision-Language Model for SVG Generation.
|
| 23 |
+
- **Language(s) (NLP):** English.
|
| 24 |
+
- **License:** Apache 2.0
|
| 25 |
+
|
| 26 |
+
### Model Architecture
|
| 27 |
+
|
| 28 |
+
The StarVector architecture integrates an image encoder and a Large Language Model (LLM) Adapter to generate SVG code from both image and text inputs. Images are first converted into embeddings using a Vision Transformer (ViT), after which the LLM Adapter maps these embeddings into the LLM's embedding space to create visual tokens. Text prompts are handled through the LLM’s tokenizer and embedder. This unified multimodal approach ensures precise and contextually rich SVG output.
|
| 29 |
+
|
| 30 |
+
<figure>
|
| 31 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65c27c201b5b51dd4814fcd2/IVGxASfNr8wfu-agH9Nqj.png" alt="Figure 2: StarVector Architecture">
|
| 32 |
+
<figcaption>Figure 2: a) StarVector Architecture: StarVector projects images into embeddings via an image encoder, then maps these embeddings to the LLM hidden space using an LLM Adapter, generating Visual Tokens. Text conditioning is achieved with the LLM's tokenizer and embedder. The model learns to map token sequences (visual or textual) to SVG code. The symbol ⊕ denotes mutually exclusive operations (image-to- SVG or text-to-SVG), while ‖ indicates sequence concatenation. Figure 2: b)Vision Model and Adapter: The image encoder employs a Vision Transformer (ViT) to process image patches sequentially. The LLM Adapter non-linearly projects embeddings into visual tokens for LLM integration.</figcaption>
|
| 33 |
+
</figure>
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
### Model Sources
|
| 38 |
+
|
| 39 |
+
- **Repository:** [https://github.com/joanrod/star-vector](https://github.com/joanrod/star-vector)
|
| 40 |
+
- **Paper:** [https://arxiv.org/abs/2312.11556](https://arxiv.org/abs/2312.11556)
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
Image-to-SVG generation, Text-to-SVG generation.
|
| 47 |
+
|
| 48 |
+
### Downstream Use
|
| 49 |
+
|
| 50 |
+
Creation of icons, logotypes, technical diagrams, and other vector graphics.
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
Generating realistic photographic images or complex 3D graphics.
|
| 55 |
+
|
| 56 |
+
## Bias, Risks, and Limitations
|
| 57 |
+
|
| 58 |
+
Potential biases may exist in the model due to the composition of the training data (SVG-Stack). The model's ability to perfectly vectorize all types of images and interpret all textual instructions may have limitations. Users should be aware of these potential issues, especially in critical applications.
|
| 59 |
+
|
| 60 |
+
### Recommendations
|
| 61 |
+
|
| 62 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Further investigation into the model's behavior across different types of inputs is recommended.
|
| 63 |
+
|
| 64 |
+
## How to Get Started with the Model
|
| 65 |
+
|
| 66 |
+
Use the code below to get started with the model.
|
| 67 |
+
|
| 68 |
+
```Python
|
| 69 |
+
from PIL import Image
|
| 70 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoProcessor
|
| 71 |
+
from starvector.data.util import process_and_rasterize_svg
|
| 72 |
+
import torch
|
| 73 |
+
|
| 74 |
+
model_name = "starvector/starvector-1b-im2svg"
|
| 75 |
+
|
| 76 |
+
starvector = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, trust_remote_code=True)
|
| 77 |
+
processor = starvector.model.processor
|
| 78 |
+
tokenizer = starvector.model.svg_transformer.tokenizer
|
| 79 |
+
|
| 80 |
+
starvector.cuda()
|
| 81 |
+
starvector.eval()
|
| 82 |
+
|
| 83 |
+
image_pil = Image.open('assets/examples/sample-18.png')
|
| 84 |
+
|
| 85 |
+
image = processor(image_pil, return_tensors="pt")['pixel_values'].cuda()
|
| 86 |
+
if not image.shape[0] == 1:
|
| 87 |
+
image = image.squeeze(0)
|
| 88 |
+
batch = {"image": image}
|
| 89 |
+
|
| 90 |
+
raw_svg = starvector.generate_im2svg(batch, max_length=4000)[0]
|
| 91 |
+
svg, raster_image = process_and_rasterize_svg(raw_svg)
|
| 92 |
+
```
|
| 93 |
+
|
| 94 |
+
## Training Details
|
| 95 |
+
### Training Data
|
| 96 |
+
SVG-Stack: A dataset of over 2 million SVG samples.
|
| 97 |
+
|
| 98 |
+
### Training Procedure
|
| 99 |
+
The model utilizes a Vision-Language Modeling architecture. Images are projected into embeddings via an image encoder, then mapped to the LLM hidden space using an LLM Adapter, generating Visual Tokens. Text conditioning is achieved with the LLM's tokenizer and embedder. The model learns to map token sequences (visual or textual) to SVG code.
|
| 100 |
+
|
| 101 |
+
## Evaluation
|
| 102 |
+
### Testing Data & Factors
|
| 103 |
+
#### Testing Data
|
| 104 |
+
SVG-Bench
|
| 105 |
+
|
| 106 |
+
#### Factors
|
| 107 |
+
SVG-Stack, SVG-Fonts, SVG-Icons, SVG-Emoji, SVG-Diagrams.
|
| 108 |
+
|
| 109 |
+
## Models
|
| 110 |
+
|
| 111 |
+
StarVector models achieve state-of-the-art performance on SVG generation tasks
|
| 112 |
+
|
| 113 |
+
We provide [Hugging Face 🤗 model checkpoints](https://huggingface.co/collections/starvector/starvector-models-6783b22c7bd4b43d13cb5289) for image2SVG vectorization, for 💫 StarVector-8B and 💫 StarVector-1B. These are the results on SVG-Bench, using the DinoScore metric.
|
| 114 |
+
|
| 115 |
+
| Method | SVG-Stack | SVG-Fonts | SVG-Icons | SVG-Emoji | SVG-Diagrams |
|
| 116 |
+
|--------------------|-----------|-----------|-----------|-----------|--------------|
|
| 117 |
+
| AutoTrace | 0.942 | 0.954 | 0.946 | 0.975 | 0.874 |
|
| 118 |
+
| Potrace | 0.898 | 0.967 | 0.972 | 0.882 | 0.875 |
|
| 119 |
+
| VTracer | 0.954 | 0.964 | 0.940 | 0.981 | 0.882 |
|
| 120 |
+
| Im2Vec | 0.692 | 0.733 | 0.754 | 0.732 | - |
|
| 121 |
+
| LIVE | 0.934 | 0.956 | 0.959 | 0.969 | 0.870 |
|
| 122 |
+
| DiffVG | 0.810 | 0.821 | 0.952 | 0.814 | 0.822 |
|
| 123 |
+
| GPT-4-V | 0.852 | 0.842 | 0.848 | 0.850 | - |
|
| 124 |
+
| 💫 **StarVector-1B** | 0.926 | 0.978 | 0.975 | 0.929 | 0.943 |
|
| 125 |
+
| 💫 **StarVector-8B** | 0.966 | 0.982 | 0.984 | 0.981 | 0.959 |
|
| 126 |
+
|
| 127 |
+
**Note:** StarVector models will not work for natural images or illustrations, as they have not been trained on those images. They excel in vectorizing icons, logotypes, technical diagrams, graphs, and charts.
|
| 128 |
+
|
| 129 |
+
As shown in the table above, StarVector-8B achieves the highest performance across all benchmark datasets, demonstrating its effectiveness in generating high-quality SVG code from images. The model's ability to understand and reproduce complex vector graphics makes it particularly valuable for applications requiring precise vectorization of icons, logos, and technical diagrams.
|
| 130 |
+
|
| 131 |
+
## Summary
|
| 132 |
+
StarVector represents a significant advancement in the field of vector graphics generation. By combining the power of vision-language models with a comprehensive training dataset, we've created a system that can accurately translate images into high-quality SVG code. The model's performance on SVG-Bench demonstrates its effectiveness across a wide range of vector graphics tasks.
|
| 133 |
+
|
| 134 |
+
We believe that StarVector will enable new applications in design, illustration, and technical documentation, making vector graphics more accessible and easier to create. We invite the research community to build upon our work and explore new directions in this exciting field.
|
| 135 |
+
|
| 136 |
+
For more details, please refer to our [paper](https://arxiv.org/abs/2312.11556) and explore our [code](https://github.com/joanrod/star-vector) repository.
|
| 137 |
+
|
| 138 |
+
## BibTeX entry and citation info
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
```
|
| 142 |
+
@misc{rodriguez2024starvector,
|
| 143 |
+
title={StarVector: Generating Scalable Vector Graphics Code from Images and Text},
|
| 144 |
+
author={Juan A. Rodriguez and Abhay Puri and Shubham Agarwal and Issam H. Laradji and Pau Rodriguez and Sai Rajeswar and David Vazquez and Christopher Pal and Marco Pedersoli},
|
| 145 |
+
year={2024},
|
| 146 |
+
eprint={2312.11556},
|
| 147 |
+
archivePrefix={arXiv},
|
| 148 |
+
primaryClass={cs.CV},
|
| 149 |
+
url={https://arxiv.org/abs/2312.11556},
|
| 150 |
+
}
|
| 151 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<caption-start>": 49155,
|
| 3 |
+
"<image-start>": 49154,
|
| 4 |
+
"<svg-start>": 49153,
|
| 5 |
+
"[PAD]": 49152
|
| 6 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ServiceNow/starvector-1b-im2svg",
|
| 3 |
+
"adapter_norm": "batch_norm",
|
| 4 |
+
"adapter_size": "large",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"StarVectorForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "starvector_arch.StarVectorConfig",
|
| 10 |
+
"AutoModelForCausalLM": "starvector_arch.StarVectorForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"dropout": 0.1,
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"hidden_size_scale": 2,
|
| 15 |
+
"image_encoder_type": "clip",
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"init_type": "glorot",
|
| 18 |
+
"max_length_train": 8192,
|
| 19 |
+
"max_position_embeddings": 8192,
|
| 20 |
+
"model_type": "starvector",
|
| 21 |
+
"multi_query": true,
|
| 22 |
+
"num_attention_heads": 16,
|
| 23 |
+
"num_hidden_layers": 24,
|
| 24 |
+
"num_kv_heads": 4,
|
| 25 |
+
"starcoder_model_name": "bigcode/starcoderbase-1b",
|
| 26 |
+
"torch_dtype": "float16",
|
| 27 |
+
"train_LLM": true,
|
| 28 |
+
"train_image_encoder": false,
|
| 29 |
+
"transformers_version": "4.40.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"use_flash_attn": true,
|
| 32 |
+
"vocab_size": 49156,
|
| 33 |
+
"image_token_index": 49154
|
| 34 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bea3a2add4a0107ae405391eaaefd7b95339d33b1ad98ed87862716ebdc02c20
|
| 3 |
+
size 4995740600
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c71c1a94c42a1408f4a75e519814f10005061a0a81a3c87f0f136d475fa916b6
|
| 3 |
+
size 146964720
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,591 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 5142622224
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.image_encoder.ln_vision.bias": "model-00002-of-00002.safetensors",
|
| 7 |
+
"model.image_encoder.ln_vision.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.image_encoder.visual_encoder.class_embedding": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.image_encoder.visual_encoder.conv1.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.image_encoder.visual_encoder.ln_pre.bias": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.image_encoder.visual_encoder.ln_pre.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.image_encoder.visual_encoder.positional_embedding": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.17.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 142 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.18.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 146 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 148 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 150 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.19.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.20.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.attn.in_proj_bias": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.attn.in_proj_weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.ln_1.bias": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.ln_1.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.ln_2.bias": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.ln_2.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.image_encoder.visual_encoder.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.image_projection.c_fc.bias": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.image_projection.c_fc.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.image_projection.c_proj.bias": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.image_projection.c_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.image_projection.norm.bias": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.image_projection.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.image_projection.norm.running_mean": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.image_projection.norm.running_var": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.image_projection.norm.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.svg_transformer.transformer.transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.svg_transformer.transformer.transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.svg_transformer.transformer.transformer.h.0.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.svg_transformer.transformer.transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.svg_transformer.transformer.transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.svg_transformer.transformer.transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.svg_transformer.transformer.transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.svg_transformer.transformer.transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.svg_transformer.transformer.transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.svg_transformer.transformer.transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.svg_transformer.transformer.transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.svg_transformer.transformer.transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.svg_transformer.transformer.transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.svg_transformer.transformer.transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.svg_transformer.transformer.transformer.h.1.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.svg_transformer.transformer.transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.svg_transformer.transformer.transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.svg_transformer.transformer.transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.svg_transformer.transformer.transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.svg_transformer.transformer.transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.svg_transformer.transformer.transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.svg_transformer.transformer.transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.svg_transformer.transformer.transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.svg_transformer.transformer.transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.svg_transformer.transformer.transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.svg_transformer.transformer.transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.svg_transformer.transformer.transformer.h.10.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.svg_transformer.transformer.transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.svg_transformer.transformer.transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.svg_transformer.transformer.transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.svg_transformer.transformer.transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.svg_transformer.transformer.transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.svg_transformer.transformer.transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.svg_transformer.transformer.transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.svg_transformer.transformer.transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.svg_transformer.transformer.transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.svg_transformer.transformer.transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.svg_transformer.transformer.transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.svg_transformer.transformer.transformer.h.11.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.svg_transformer.transformer.transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.svg_transformer.transformer.transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.svg_transformer.transformer.transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.svg_transformer.transformer.transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.svg_transformer.transformer.transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.svg_transformer.transformer.transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.svg_transformer.transformer.transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.svg_transformer.transformer.transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.svg_transformer.transformer.transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.svg_transformer.transformer.transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.svg_transformer.transformer.transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.svg_transformer.transformer.transformer.h.12.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.svg_transformer.transformer.transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.svg_transformer.transformer.transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.svg_transformer.transformer.transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.svg_transformer.transformer.transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.svg_transformer.transformer.transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.svg_transformer.transformer.transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.svg_transformer.transformer.transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.svg_transformer.transformer.transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.svg_transformer.transformer.transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.svg_transformer.transformer.transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.svg_transformer.transformer.transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.svg_transformer.transformer.transformer.h.13.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.svg_transformer.transformer.transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.svg_transformer.transformer.transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.svg_transformer.transformer.transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.svg_transformer.transformer.transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.svg_transformer.transformer.transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.svg_transformer.transformer.transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.svg_transformer.transformer.transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.svg_transformer.transformer.transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.svg_transformer.transformer.transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.svg_transformer.transformer.transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.svg_transformer.transformer.transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.svg_transformer.transformer.transformer.h.14.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.svg_transformer.transformer.transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.svg_transformer.transformer.transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.svg_transformer.transformer.transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.svg_transformer.transformer.transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.svg_transformer.transformer.transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.svg_transformer.transformer.transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.svg_transformer.transformer.transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.svg_transformer.transformer.transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.svg_transformer.transformer.transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.svg_transformer.transformer.transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.svg_transformer.transformer.transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.svg_transformer.transformer.transformer.h.15.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.svg_transformer.transformer.transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.svg_transformer.transformer.transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.svg_transformer.transformer.transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.svg_transformer.transformer.transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.svg_transformer.transformer.transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.svg_transformer.transformer.transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.svg_transformer.transformer.transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.svg_transformer.transformer.transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.svg_transformer.transformer.transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.svg_transformer.transformer.transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.svg_transformer.transformer.transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.svg_transformer.transformer.transformer.h.16.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.svg_transformer.transformer.transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.svg_transformer.transformer.transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.svg_transformer.transformer.transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.svg_transformer.transformer.transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.svg_transformer.transformer.transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.svg_transformer.transformer.transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.svg_transformer.transformer.transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.svg_transformer.transformer.transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.svg_transformer.transformer.transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.svg_transformer.transformer.transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.svg_transformer.transformer.transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.svg_transformer.transformer.transformer.h.17.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.svg_transformer.transformer.transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.svg_transformer.transformer.transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.svg_transformer.transformer.transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.svg_transformer.transformer.transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.svg_transformer.transformer.transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.svg_transformer.transformer.transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.svg_transformer.transformer.transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.svg_transformer.transformer.transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.svg_transformer.transformer.transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.svg_transformer.transformer.transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.svg_transformer.transformer.transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.svg_transformer.transformer.transformer.h.18.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.svg_transformer.transformer.transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.svg_transformer.transformer.transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.svg_transformer.transformer.transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.svg_transformer.transformer.transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.svg_transformer.transformer.transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.svg_transformer.transformer.transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.svg_transformer.transformer.transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.svg_transformer.transformer.transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.svg_transformer.transformer.transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.svg_transformer.transformer.transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.svg_transformer.transformer.transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.svg_transformer.transformer.transformer.h.19.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.svg_transformer.transformer.transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.svg_transformer.transformer.transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.svg_transformer.transformer.transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.svg_transformer.transformer.transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.svg_transformer.transformer.transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.svg_transformer.transformer.transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.svg_transformer.transformer.transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.svg_transformer.transformer.transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.svg_transformer.transformer.transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.svg_transformer.transformer.transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.svg_transformer.transformer.transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.svg_transformer.transformer.transformer.h.2.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.svg_transformer.transformer.transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.svg_transformer.transformer.transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.svg_transformer.transformer.transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.svg_transformer.transformer.transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.svg_transformer.transformer.transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.svg_transformer.transformer.transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.svg_transformer.transformer.transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.svg_transformer.transformer.transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.svg_transformer.transformer.transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.svg_transformer.transformer.transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.svg_transformer.transformer.transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.svg_transformer.transformer.transformer.h.20.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.svg_transformer.transformer.transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.svg_transformer.transformer.transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.svg_transformer.transformer.transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.svg_transformer.transformer.transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.svg_transformer.transformer.transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.svg_transformer.transformer.transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.svg_transformer.transformer.transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.svg_transformer.transformer.transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.svg_transformer.transformer.transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.svg_transformer.transformer.transformer.h.21.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.svg_transformer.transformer.transformer.h.21.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.svg_transformer.transformer.transformer.h.21.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.svg_transformer.transformer.transformer.h.21.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.svg_transformer.transformer.transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.svg_transformer.transformer.transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.svg_transformer.transformer.transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.svg_transformer.transformer.transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.svg_transformer.transformer.transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.svg_transformer.transformer.transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.svg_transformer.transformer.transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.svg_transformer.transformer.transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.svg_transformer.transformer.transformer.h.22.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.svg_transformer.transformer.transformer.h.22.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.svg_transformer.transformer.transformer.h.22.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.svg_transformer.transformer.transformer.h.22.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.svg_transformer.transformer.transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.svg_transformer.transformer.transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.svg_transformer.transformer.transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.svg_transformer.transformer.transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.svg_transformer.transformer.transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.svg_transformer.transformer.transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.svg_transformer.transformer.transformer.h.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.svg_transformer.transformer.transformer.h.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.svg_transformer.transformer.transformer.h.23.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.svg_transformer.transformer.transformer.h.23.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.svg_transformer.transformer.transformer.h.23.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.svg_transformer.transformer.transformer.h.23.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.svg_transformer.transformer.transformer.h.23.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.svg_transformer.transformer.transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.svg_transformer.transformer.transformer.h.23.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.svg_transformer.transformer.transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.svg_transformer.transformer.transformer.h.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.svg_transformer.transformer.transformer.h.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.svg_transformer.transformer.transformer.h.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.svg_transformer.transformer.transformer.h.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.svg_transformer.transformer.transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.svg_transformer.transformer.transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.svg_transformer.transformer.transformer.h.3.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.svg_transformer.transformer.transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.svg_transformer.transformer.transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.svg_transformer.transformer.transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.svg_transformer.transformer.transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.svg_transformer.transformer.transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.svg_transformer.transformer.transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.svg_transformer.transformer.transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.svg_transformer.transformer.transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.svg_transformer.transformer.transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.svg_transformer.transformer.transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.svg_transformer.transformer.transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.svg_transformer.transformer.transformer.h.4.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.svg_transformer.transformer.transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.svg_transformer.transformer.transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.svg_transformer.transformer.transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.svg_transformer.transformer.transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.svg_transformer.transformer.transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.svg_transformer.transformer.transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.svg_transformer.transformer.transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.svg_transformer.transformer.transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.svg_transformer.transformer.transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.svg_transformer.transformer.transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.svg_transformer.transformer.transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.svg_transformer.transformer.transformer.h.5.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.svg_transformer.transformer.transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.svg_transformer.transformer.transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.svg_transformer.transformer.transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.svg_transformer.transformer.transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.svg_transformer.transformer.transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.svg_transformer.transformer.transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.svg_transformer.transformer.transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.svg_transformer.transformer.transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.svg_transformer.transformer.transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.svg_transformer.transformer.transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.svg_transformer.transformer.transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.svg_transformer.transformer.transformer.h.6.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.svg_transformer.transformer.transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.svg_transformer.transformer.transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.svg_transformer.transformer.transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.svg_transformer.transformer.transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.svg_transformer.transformer.transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.svg_transformer.transformer.transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.svg_transformer.transformer.transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.svg_transformer.transformer.transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.svg_transformer.transformer.transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.svg_transformer.transformer.transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.svg_transformer.transformer.transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.svg_transformer.transformer.transformer.h.7.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.svg_transformer.transformer.transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.svg_transformer.transformer.transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.svg_transformer.transformer.transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.svg_transformer.transformer.transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.svg_transformer.transformer.transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.svg_transformer.transformer.transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.svg_transformer.transformer.transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.svg_transformer.transformer.transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.svg_transformer.transformer.transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.svg_transformer.transformer.transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.svg_transformer.transformer.transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.svg_transformer.transformer.transformer.h.8.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.svg_transformer.transformer.transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.svg_transformer.transformer.transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.svg_transformer.transformer.transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.svg_transformer.transformer.transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.svg_transformer.transformer.transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.svg_transformer.transformer.transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.svg_transformer.transformer.transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.svg_transformer.transformer.transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.svg_transformer.transformer.transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.svg_transformer.transformer.transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.svg_transformer.transformer.transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.svg_transformer.transformer.transformer.h.9.attn.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.svg_transformer.transformer.transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.svg_transformer.transformer.transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.svg_transformer.transformer.transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.svg_transformer.transformer.transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.svg_transformer.transformer.transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.svg_transformer.transformer.transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.svg_transformer.transformer.transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.svg_transformer.transformer.transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.svg_transformer.transformer.transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.svg_transformer.transformer.transformer.ln_f.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.svg_transformer.transformer.transformer.ln_f.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.svg_transformer.transformer.transformer.wpe.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.svg_transformer.transformer.transformer.wte.weight": "model-00001-of-00002.safetensors"
|
| 590 |
+
}
|
| 591 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor_type": "SimpleStarVectorProcessor",
|
| 3 |
+
"mean": [
|
| 4 |
+
0.48145466,
|
| 5 |
+
0.4578275,
|
| 6 |
+
0.40821073
|
| 7 |
+
],
|
| 8 |
+
"image_std": [
|
| 9 |
+
0.26862954,
|
| 10 |
+
0.26130258,
|
| 11 |
+
0.27577711
|
| 12 |
+
],
|
| 13 |
+
"size": 224
|
| 14 |
+
}
|
processing_starvector.py
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers.processing_utils import ProcessorMixin
|
| 2 |
+
from torchvision import transforms
|
| 3 |
+
from torchvision.transforms.functional import InterpolationMode, pad
|
| 4 |
+
from transformers.feature_extraction_sequence_utils import BatchFeature
|
| 5 |
+
|
| 6 |
+
class SimpleStarVectorProcessor(ProcessorMixin):
|
| 7 |
+
attributes = ["tokenizer"] # Only include tokenizer in attributes
|
| 8 |
+
valid_kwargs = ["size", "mean", "std"] # Add other parameters as valid kwargs
|
| 9 |
+
image_processor_class = "AutoImageProcessor"
|
| 10 |
+
tokenizer_class = "AutoTokenizer"
|
| 11 |
+
|
| 12 |
+
def __init__(self,
|
| 13 |
+
tokenizer=None, # Make tokenizer the first argument
|
| 14 |
+
size=224,
|
| 15 |
+
mean=None,
|
| 16 |
+
std=None,
|
| 17 |
+
**kwargs,
|
| 18 |
+
):
|
| 19 |
+
if mean is None:
|
| 20 |
+
mean = (0.48145466, 0.4578275, 0.40821073)
|
| 21 |
+
if std is None:
|
| 22 |
+
std = (0.26862954, 0.26130258, 0.27577711)
|
| 23 |
+
|
| 24 |
+
# Store these as instance variables
|
| 25 |
+
self.mean = mean
|
| 26 |
+
self.std = std
|
| 27 |
+
self.size = size
|
| 28 |
+
|
| 29 |
+
self.normalize = transforms.Normalize(mean=mean, std=std)
|
| 30 |
+
|
| 31 |
+
self.transform = transforms.Compose([
|
| 32 |
+
transforms.Lambda(lambda img: img.convert("RGB") if img.mode == "RGBA" else img),
|
| 33 |
+
transforms.Lambda(lambda img: self._pad_to_square(img)),
|
| 34 |
+
transforms.Resize(size, interpolation=InterpolationMode.BICUBIC),
|
| 35 |
+
transforms.ToTensor(),
|
| 36 |
+
self.normalize
|
| 37 |
+
])
|
| 38 |
+
|
| 39 |
+
# Initialize parent class with tokenizer
|
| 40 |
+
super().__init__(tokenizer=tokenizer)
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
def __call__(self, images=None, text=None, **kwargs) -> BatchFeature:
|
| 44 |
+
"""
|
| 45 |
+
Process images and/or text inputs.
|
| 46 |
+
|
| 47 |
+
Args:
|
| 48 |
+
images: Optional image input(s)
|
| 49 |
+
text: Optional text input(s)
|
| 50 |
+
**kwargs: Additional arguments
|
| 51 |
+
"""
|
| 52 |
+
if images is None and text is None:
|
| 53 |
+
raise ValueError("You have to specify at least one of `images` or `text`.")
|
| 54 |
+
|
| 55 |
+
image_inputs = {}
|
| 56 |
+
if images is not None:
|
| 57 |
+
if isinstance(images, (list, tuple)):
|
| 58 |
+
images_ = [self.transform(img) for img in images]
|
| 59 |
+
else:
|
| 60 |
+
images_ = self.transform(images)
|
| 61 |
+
image_inputs = {"pixel_values": images_}
|
| 62 |
+
|
| 63 |
+
text_inputs = {}
|
| 64 |
+
if text is not None:
|
| 65 |
+
text_inputs = self.tokenizer(text, **kwargs)
|
| 66 |
+
return BatchFeature(data={**text_inputs, **image_inputs})
|
| 67 |
+
|
| 68 |
+
def _pad_to_square(self, img):
|
| 69 |
+
# Calculate padding to make the image square
|
| 70 |
+
width, height = img.size
|
| 71 |
+
max_dim = max(width, height)
|
| 72 |
+
padding = [(max_dim - width) // 2, (max_dim - height) // 2]
|
| 73 |
+
padding += [max_dim - width - padding[0], max_dim - height - padding[1]]
|
| 74 |
+
return pad(img, padding, fill=255) # Assuming white padding
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
AutoProcessor.register(SimpleStarVectorProcessor, SimpleStarVectorProcessor)
|
processor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mean": [
|
| 3 |
+
0.48145466,
|
| 4 |
+
0.4578275,
|
| 5 |
+
0.40821073
|
| 6 |
+
],
|
| 7 |
+
"processor_class": "SimpleStarVectorProcessor",
|
| 8 |
+
"size": 224,
|
| 9 |
+
"std": [
|
| 10 |
+
0.26862954,
|
| 11 |
+
0.26130258,
|
| 12 |
+
0.27577711
|
| 13 |
+
]
|
| 14 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": {
|
| 38 |
+
"content": "[PAD]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<|endoftext|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
starvector_arch.py
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import (
|
| 2 |
+
PretrainedConfig,
|
| 3 |
+
PreTrainedModel
|
| 4 |
+
)
|
| 5 |
+
from torch.nn import CrossEntropyLoss
|
| 6 |
+
from transformers.models.gpt_bigcode.modeling_gpt_bigcode import CausalLMOutputWithCrossAttentions
|
| 7 |
+
from typing import Optional, Tuple, Union
|
| 8 |
+
import torch
|
| 9 |
+
|
| 10 |
+
from transformers.processing_utils import ProcessorMixin
|
| 11 |
+
from torchvision import transforms
|
| 12 |
+
from torchvision.transforms.functional import InterpolationMode, pad
|
| 13 |
+
from transformers.feature_extraction_sequence_utils import BatchFeature
|
| 14 |
+
from transformers import AutoProcessor
|
| 15 |
+
|
| 16 |
+
class SimpleStarVectorProcessor(ProcessorMixin):
|
| 17 |
+
attributes = ["tokenizer"] # Only include tokenizer in attributes
|
| 18 |
+
valid_kwargs = ["size", "mean", "std"] # Add other parameters as valid kwargs
|
| 19 |
+
image_processor_class = "AutoImageProcessor"
|
| 20 |
+
tokenizer_class = "AutoTokenizer"
|
| 21 |
+
|
| 22 |
+
def __init__(self,
|
| 23 |
+
tokenizer=None, # Make tokenizer the first argument
|
| 24 |
+
size=224,
|
| 25 |
+
mean=None,
|
| 26 |
+
std=None,
|
| 27 |
+
**kwargs,
|
| 28 |
+
):
|
| 29 |
+
if mean is None:
|
| 30 |
+
mean = (0.48145466, 0.4578275, 0.40821073)
|
| 31 |
+
if std is None:
|
| 32 |
+
std = (0.26862954, 0.26130258, 0.27577711)
|
| 33 |
+
|
| 34 |
+
# Store these as instance variables
|
| 35 |
+
self.mean = mean
|
| 36 |
+
self.std = std
|
| 37 |
+
self.size = size
|
| 38 |
+
self.normalize = transforms.Normalize(mean=mean, std=std)
|
| 39 |
+
|
| 40 |
+
self.transform = transforms.Compose([
|
| 41 |
+
transforms.Lambda(lambda img: img.convert("RGB") if img.mode == "RGBA" else img),
|
| 42 |
+
transforms.Lambda(lambda img: self._pad_to_square(img)),
|
| 43 |
+
transforms.Resize(size, interpolation=InterpolationMode.BICUBIC),
|
| 44 |
+
transforms.ToTensor(),
|
| 45 |
+
self.normalize
|
| 46 |
+
])
|
| 47 |
+
|
| 48 |
+
# Initialize parent class with tokenizer
|
| 49 |
+
super().__init__(tokenizer=tokenizer)
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def __call__(self, images=None, text=None, max_length=None, **kwargs) -> BatchFeature:
|
| 53 |
+
"""
|
| 54 |
+
Process images and/or text inputs.
|
| 55 |
+
|
| 56 |
+
Args:
|
| 57 |
+
images: Optional image input(s)
|
| 58 |
+
text: Optional text input(s)
|
| 59 |
+
**kwargs: Additional arguments
|
| 60 |
+
"""
|
| 61 |
+
if images is None and text is None:
|
| 62 |
+
raise ValueError("You have to specify at least one of `images` or `text`.")
|
| 63 |
+
|
| 64 |
+
image_inputs = {}
|
| 65 |
+
if images is not None:
|
| 66 |
+
if isinstance(images, (list, tuple)):
|
| 67 |
+
images_ = torch.stack([self.transform(img) for img in images])
|
| 68 |
+
else:
|
| 69 |
+
images_ = self.transform(images)
|
| 70 |
+
image_inputs = {"pixel_values": images_}
|
| 71 |
+
|
| 72 |
+
text_inputs = {}
|
| 73 |
+
if text is not None:
|
| 74 |
+
text_inputs = self.tokenizer(
|
| 75 |
+
text, truncation=True,
|
| 76 |
+
add_special_tokens=True,
|
| 77 |
+
padding='longest',
|
| 78 |
+
max_length=max_length,
|
| 79 |
+
return_tensors="pt"
|
| 80 |
+
)
|
| 81 |
+
|
| 82 |
+
return BatchFeature(data={**text_inputs, **image_inputs})
|
| 83 |
+
|
| 84 |
+
def _pad_to_square(self, img):
|
| 85 |
+
# Calculate padding to make the image square
|
| 86 |
+
width, height = img.size
|
| 87 |
+
max_dim = max(width, height)
|
| 88 |
+
padding = [(max_dim - width) // 2, (max_dim - height) // 2]
|
| 89 |
+
padding += [max_dim - width - padding[0], max_dim - height - padding[1]]
|
| 90 |
+
return pad(img, padding, fill=255) # Assuming white padding
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
AutoProcessor.register(SimpleStarVectorProcessor, SimpleStarVectorProcessor)
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
class StarVectorConfig(PretrainedConfig):
|
| 97 |
+
model_type = "starvector"
|
| 98 |
+
|
| 99 |
+
def __init__(
|
| 100 |
+
self,
|
| 101 |
+
starcoder_model_name: str = "bigcode/starcoderbase-1b",
|
| 102 |
+
image_encoder_type: str = "clip",
|
| 103 |
+
adapter_norm: str = "layer_norm",
|
| 104 |
+
image_size: int = 224,
|
| 105 |
+
max_length: int = 8192,
|
| 106 |
+
max_length_train: int = 8192,
|
| 107 |
+
use_flash_attn: bool = True,
|
| 108 |
+
use_cache: bool = True,
|
| 109 |
+
num_attention_heads: int = 16,
|
| 110 |
+
num_hidden_layers: int = 24,
|
| 111 |
+
vocab_size: int = 49152,
|
| 112 |
+
hidden_size: int = 2048,
|
| 113 |
+
num_kv_heads: int = 4,
|
| 114 |
+
torch_dtype: str = "bfloat16",
|
| 115 |
+
**kwargs,
|
| 116 |
+
):
|
| 117 |
+
kwargs["torch_dtype"] = torch_dtype
|
| 118 |
+
self.starcoder_model_name = starcoder_model_name
|
| 119 |
+
self.image_encoder_type = image_encoder_type
|
| 120 |
+
self.adapter_norm = adapter_norm
|
| 121 |
+
self.image_size = image_size
|
| 122 |
+
self.max_length = max_length
|
| 123 |
+
self.max_length_train = max_length_train
|
| 124 |
+
self.use_flash_attn = use_flash_attn
|
| 125 |
+
self.use_cache = use_cache
|
| 126 |
+
self.num_attention_heads = num_attention_heads
|
| 127 |
+
self.num_hidden_layers = num_hidden_layers
|
| 128 |
+
self.vocab_size = vocab_size
|
| 129 |
+
self.hidden_size = hidden_size
|
| 130 |
+
self.num_kv_heads = num_kv_heads
|
| 131 |
+
super().__init__(**kwargs)
|
| 132 |
+
|
| 133 |
+
class StarVectorForCausalLM(PreTrainedModel):
|
| 134 |
+
config_class = StarVectorConfig
|
| 135 |
+
_no_split_modules = []
|
| 136 |
+
_supports_flash_attn_2 = True
|
| 137 |
+
|
| 138 |
+
def __init__(self, config: StarVectorConfig, **kwargs):
|
| 139 |
+
super().__init__(config)
|
| 140 |
+
starcoder_model_name = config.starcoder_model_name
|
| 141 |
+
if 'starcoder2' in starcoder_model_name:
|
| 142 |
+
from starvector.model.models.starvector_v2 import StarVectorStarCoder2
|
| 143 |
+
self.model = StarVectorStarCoder2(config=config, **kwargs)
|
| 144 |
+
else:
|
| 145 |
+
from starvector.model.models.starvector_v1 import StarVectorStarCoder
|
| 146 |
+
self.model = StarVectorStarCoder(config=config, **kwargs)
|
| 147 |
+
|
| 148 |
+
|
| 149 |
+
@property
|
| 150 |
+
def supports_gradient_checkpointing(self):
|
| 151 |
+
# If the underlying transformer (e.g., the one in StarCoderModel)
|
| 152 |
+
# supports gradient checkpointing, delegate to it.
|
| 153 |
+
if hasattr(self.model, 'svg_transformer'):
|
| 154 |
+
return getattr(self.model.svg_transformer, 'supports_gradient_checkpointing', False)
|
| 155 |
+
return False
|
| 156 |
+
|
| 157 |
+
def gradient_checkpointing_enable(self):
|
| 158 |
+
# Optionally, forward this call to the internal transformer.
|
| 159 |
+
if hasattr(self.model, 'svg_transformer') and hasattr(self.model.svg_transformer, 'gradient_checkpointing_enable'):
|
| 160 |
+
self.model.svg_transformer.gradient_checkpointing_enable()
|
| 161 |
+
|
| 162 |
+
def forward(self, vision_embeds, input_ids, num_generations, num_logits_to_keep) -> Union[Tuple, CausalLMOutputWithCrossAttentions]:
|
| 163 |
+
r"""
|
| 164 |
+
Wrapper for the forward pass of the model.
|
| 165 |
+
"""
|
| 166 |
+
device = vision_embeds.device
|
| 167 |
+
|
| 168 |
+
completion_embeds = self.model._get_embeddings(input_ids)
|
| 169 |
+
vision_embeds = torch.cat([vision_embeds.repeat(num_generations, 1, 1), completion_embeds], dim=1)
|
| 170 |
+
attention_mask = torch.ones_like(vision_embeds[:, :, 0]).to(device)
|
| 171 |
+
|
| 172 |
+
transformer_outputs = self.model.svg_transformer.transformer.transformer(
|
| 173 |
+
inputs_embeds=vision_embeds,
|
| 174 |
+
attention_mask=attention_mask,
|
| 175 |
+
)
|
| 176 |
+
hidden_states = transformer_outputs[0]
|
| 177 |
+
|
| 178 |
+
if num_logits_to_keep > 0:
|
| 179 |
+
lm_logits = self.model.svg_transformer.transformer.lm_head(hidden_states[:, -num_logits_to_keep:, :])
|
| 180 |
+
else:
|
| 181 |
+
lm_logits = self.model.svg_transformer.transformer.lm_head(hidden_states)
|
| 182 |
+
loss = None
|
| 183 |
+
return CausalLMOutputWithCrossAttentions(
|
| 184 |
+
loss=loss,
|
| 185 |
+
logits=lm_logits,
|
| 186 |
+
past_key_values=transformer_outputs.past_key_values,
|
| 187 |
+
hidden_states=transformer_outputs.hidden_states,
|
| 188 |
+
attentions=transformer_outputs.attentions,
|
| 189 |
+
cross_attentions=transformer_outputs.cross_attentions,
|
| 190 |
+
)
|
| 191 |
+
|
| 192 |
+
def generate_im2svg(self, batch, **kwargs):
|
| 193 |
+
return self.model.generate_im2svg(batch, **kwargs)
|
| 194 |
+
|
| 195 |
+
def generate_im2text(self, batch, **kwargs):
|
| 196 |
+
return self.model.generate_im2text(batch, **kwargs)
|
| 197 |
+
|
| 198 |
+
def process_images(self, images):
|
| 199 |
+
return self.model.image_encoder.process_images(images)
|
| 200 |
+
|
| 201 |
+
def gradient_checkpointing_enable(self, gradient_checkpointing_kwargs=None):
|
| 202 |
+
self.model.svg_transformer.transformer.gradient_checkpointing_enable(gradient_checkpointing_kwargs=gradient_checkpointing_kwargs)
|
| 203 |
+
|
| 204 |
+
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<fim_prefix>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<fim_middle>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<fim_suffix>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<fim_pad>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<filename>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "<gh_stars>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<issue_start>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<issue_comment>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<issue_closed>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<jupyter_start>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<jupyter_text>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<jupyter_code>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<jupyter_output>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<empty_output>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<commit_before>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<commit_msg>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<commit_after>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<reponame>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"49152": {
|
| 158 |
+
"content": "[PAD]",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"49153": {
|
| 166 |
+
"content": "<svg-start>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"49154": {
|
| 174 |
+
"content": "<image-start>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"49155": {
|
| 182 |
+
"content": "<caption-start>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": true,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
}
|
| 189 |
+
},
|
| 190 |
+
"additional_special_tokens": [
|
| 191 |
+
"<|endoftext|>",
|
| 192 |
+
"<fim_prefix>",
|
| 193 |
+
"<fim_middle>",
|
| 194 |
+
"<fim_suffix>",
|
| 195 |
+
"<fim_pad>",
|
| 196 |
+
"<filename>",
|
| 197 |
+
"<gh_stars>",
|
| 198 |
+
"<issue_start>",
|
| 199 |
+
"<issue_comment>",
|
| 200 |
+
"<issue_closed>",
|
| 201 |
+
"<jupyter_start>",
|
| 202 |
+
"<jupyter_text>",
|
| 203 |
+
"<jupyter_code>",
|
| 204 |
+
"<jupyter_output>",
|
| 205 |
+
"<empty_output>",
|
| 206 |
+
"<commit_before>",
|
| 207 |
+
"<commit_msg>",
|
| 208 |
+
"<commit_after>",
|
| 209 |
+
"<reponame>"
|
| 210 |
+
],
|
| 211 |
+
"bos_token": "<|endoftext|>",
|
| 212 |
+
"clean_up_tokenization_spaces": true,
|
| 213 |
+
"eos_token": "<|endoftext|>",
|
| 214 |
+
"errors": "replace",
|
| 215 |
+
"extra_special_tokens": {},
|
| 216 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 217 |
+
"pad_token": "[PAD]",
|
| 218 |
+
"processor_class": "SimpleStarVectorProcessor",
|
| 219 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 220 |
+
"unk_token": "<|endoftext|>",
|
| 221 |
+
"vocab_size": 49152
|
| 222 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|