init
Browse files- README.md +43 -0
- assets/.DS_Store +0 -0
- assets/dataset.jpg +0 -0
- assets/pipeline.jpg +0 -0
- assets/teaser.jpg +0 -0
- assets/thumbnail.jpg +0 -0
- cvlm_llama2_tokenizer/added_tokens.json +68 -0
- cvlm_llama2_tokenizer/special_tokens_map.json +40 -0
- cvlm_llama2_tokenizer/tokenizer.model +3 -0
- cvlm_llama2_tokenizer/tokenizer_config.json +573 -0
- detokenizer/detokenizer_george_adapted/checkpoint-4000/pytorch_model.bin +3 -0
- detokenizer/detokenizer_pretrained/checkpoint-55000/pytorch_model.bin +3 -0
- seed_story/george_sft/pytorch_model.bin +3 -0
- seedx/checkpoint-30000/pytorch_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# SEED-Story
|
| 2 |
+
[](https://arxiv.org/)
|
| 3 |
+
[](https://huggingface.co/TencentARC/SEED-Story)
|
| 4 |
+
[](https://huggingface.co/datasets/TencentARC/StoryStream)
|
| 5 |
+
[](https://github.com/TencentARC/SEED-Story)
|
| 6 |
+
|
| 7 |
+
**TL;DR:** We introduce SEED-Story, a MLLM capable of generating multimodal
|
| 8 |
+
long stories consists of rich and coherent narrative texts, along with images that are consistent in characters and
|
| 9 |
+
style. We also release the StoryStream Dataset for build this model.
|
| 10 |
+
|
| 11 |
+
## Introduction
|
| 12 |
+
The introduced SEED-Story, powered by MLLM, is capable of generating multimodal long stories from user-provided images and texts as the beginning of the story. The generated story consists of rich and coherent narrative texts, along with images that are consistent in characters and style. The story can span up to 25 multimodal sequences, even though we only use a maximum of 10 sequences during training.
|
| 13 |
+
<img src="assets/teaser.jpg" width="800" alt="Teaser image">
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
Overview of the SEED-Story. Training Pipeline: In Stage 1, we pre-trains an SD-XL-based de-tokenizer to reconstruct images by taking the features of a pre-trained ViT as inputs. In Stage 2, we sample an interleaved image-text sequence of a random length and train the MLLM by performing next-word prediction and image feature regression between the output hidden states of the learnable queries and ViT features of the target image. In Stage 3, the regressed image features from the MLLM are fed into the de-tokenizer for tuning SD-XL, enhancing the consistency of the characters and styles in the generated images.
|
| 17 |
+
<img src="assets/pipeline.jpg" width="800" alt="Pipeline image">
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
## Model Weights
|
| 21 |
+
We release the pretrained Tokenizer, the pretrained De-Tokenizer, the pre-trained foundation model **SEED-X-pretrained**,
|
| 22 |
+
the StoryStream instruction-tuned MLLM **SEED-Story-George**, and the StoryStream tuned De-Tokenizer in **Detokenizer-George** [SEED-X-17B Hugging Face](https://huggingface.co/TencentARC/SEED-Story).
|
| 23 |
+
|
| 24 |
+
Please download the checkpoints and save them under the folder `./pretrained`.
|
| 25 |
+
|
| 26 |
+
You also need to download [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) and [Qwen-VL-Chat](https://huggingface.co/Qwen/Qwen-VL-Chat), and save them under the folder `./pretrained`. Please use the following script to extract the weights of visual encoder in Qwen-VL-Chat.
|
| 27 |
+
```bash
|
| 28 |
+
python3 src/tools/reload_qwen_vit.py
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
## Citation
|
| 32 |
+
If you find the work helpful, please consider citing:
|
| 33 |
+
```bash
|
| 34 |
+
@article{ge2024seed,
|
| 35 |
+
title={SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation},
|
| 36 |
+
author={Ge, Yuying and Zhao, Sijie and Zhu, Jinguo and Ge, Yixiao and Yi, Kun and Song, Lin and Li, Chen and Ding, Xiaohan and Shan, Ying},
|
| 37 |
+
journal={arXiv preprint arXiv:2404.14396},
|
| 38 |
+
year={2024}
|
| 39 |
+
}
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## License
|
| 43 |
+
`SEED-Story` is licensed under the Apache License Version 2.0 except for the third-party components listed in [License](License_Seed-Story.txt).
|
assets/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
assets/dataset.jpg
ADDED
|
assets/pipeline.jpg
ADDED
|
assets/teaser.jpg
ADDED
|
assets/thumbnail.jpg
ADDED
|
|
cvlm_llama2_tokenizer/added_tokens.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</img>": 32065,
|
| 3 |
+
"<img>": 32064,
|
| 4 |
+
"<img_00000>": 32000,
|
| 5 |
+
"<img_00001>": 32001,
|
| 6 |
+
"<img_00002>": 32002,
|
| 7 |
+
"<img_00003>": 32003,
|
| 8 |
+
"<img_00004>": 32004,
|
| 9 |
+
"<img_00005>": 32005,
|
| 10 |
+
"<img_00006>": 32006,
|
| 11 |
+
"<img_00007>": 32007,
|
| 12 |
+
"<img_00008>": 32008,
|
| 13 |
+
"<img_00009>": 32009,
|
| 14 |
+
"<img_00010>": 32010,
|
| 15 |
+
"<img_00011>": 32011,
|
| 16 |
+
"<img_00012>": 32012,
|
| 17 |
+
"<img_00013>": 32013,
|
| 18 |
+
"<img_00014>": 32014,
|
| 19 |
+
"<img_00015>": 32015,
|
| 20 |
+
"<img_00016>": 32016,
|
| 21 |
+
"<img_00017>": 32017,
|
| 22 |
+
"<img_00018>": 32018,
|
| 23 |
+
"<img_00019>": 32019,
|
| 24 |
+
"<img_00020>": 32020,
|
| 25 |
+
"<img_00021>": 32021,
|
| 26 |
+
"<img_00022>": 32022,
|
| 27 |
+
"<img_00023>": 32023,
|
| 28 |
+
"<img_00024>": 32024,
|
| 29 |
+
"<img_00025>": 32025,
|
| 30 |
+
"<img_00026>": 32026,
|
| 31 |
+
"<img_00027>": 32027,
|
| 32 |
+
"<img_00028>": 32028,
|
| 33 |
+
"<img_00029>": 32029,
|
| 34 |
+
"<img_00030>": 32030,
|
| 35 |
+
"<img_00031>": 32031,
|
| 36 |
+
"<img_00032>": 32032,
|
| 37 |
+
"<img_00033>": 32033,
|
| 38 |
+
"<img_00034>": 32034,
|
| 39 |
+
"<img_00035>": 32035,
|
| 40 |
+
"<img_00036>": 32036,
|
| 41 |
+
"<img_00037>": 32037,
|
| 42 |
+
"<img_00038>": 32038,
|
| 43 |
+
"<img_00039>": 32039,
|
| 44 |
+
"<img_00040>": 32040,
|
| 45 |
+
"<img_00041>": 32041,
|
| 46 |
+
"<img_00042>": 32042,
|
| 47 |
+
"<img_00043>": 32043,
|
| 48 |
+
"<img_00044>": 32044,
|
| 49 |
+
"<img_00045>": 32045,
|
| 50 |
+
"<img_00046>": 32046,
|
| 51 |
+
"<img_00047>": 32047,
|
| 52 |
+
"<img_00048>": 32048,
|
| 53 |
+
"<img_00049>": 32049,
|
| 54 |
+
"<img_00050>": 32050,
|
| 55 |
+
"<img_00051>": 32051,
|
| 56 |
+
"<img_00052>": 32052,
|
| 57 |
+
"<img_00053>": 32053,
|
| 58 |
+
"<img_00054>": 32054,
|
| 59 |
+
"<img_00055>": 32055,
|
| 60 |
+
"<img_00056>": 32056,
|
| 61 |
+
"<img_00057>": 32057,
|
| 62 |
+
"<img_00058>": 32058,
|
| 63 |
+
"<img_00059>": 32059,
|
| 64 |
+
"<img_00060>": 32060,
|
| 65 |
+
"<img_00061>": 32061,
|
| 66 |
+
"<img_00062>": 32062,
|
| 67 |
+
"<img_00063>": 32063
|
| 68 |
+
}
|
cvlm_llama2_tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<img>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "</img>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"bos_token": {
|
| 19 |
+
"content": "<s>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"eos_token": {
|
| 26 |
+
"content": "</s>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"pad_token": "<unk>",
|
| 33 |
+
"unk_token": {
|
| 34 |
+
"content": "<unk>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
cvlm_llama2_tokenizer/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
cvlm_llama2_tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<img_00000>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"32001": {
|
| 38 |
+
"content": "<img_00001>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"32002": {
|
| 46 |
+
"content": "<img_00002>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"32003": {
|
| 54 |
+
"content": "<img_00003>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"32004": {
|
| 62 |
+
"content": "<img_00004>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"32005": {
|
| 70 |
+
"content": "<img_00005>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"32006": {
|
| 78 |
+
"content": "<img_00006>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"32007": {
|
| 86 |
+
"content": "<img_00007>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"32008": {
|
| 94 |
+
"content": "<img_00008>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"32009": {
|
| 102 |
+
"content": "<img_00009>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"32010": {
|
| 110 |
+
"content": "<img_00010>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"32011": {
|
| 118 |
+
"content": "<img_00011>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"32012": {
|
| 126 |
+
"content": "<img_00012>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"32013": {
|
| 134 |
+
"content": "<img_00013>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"32014": {
|
| 142 |
+
"content": "<img_00014>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"32015": {
|
| 150 |
+
"content": "<img_00015>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"32016": {
|
| 158 |
+
"content": "<img_00016>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"32017": {
|
| 166 |
+
"content": "<img_00017>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"32018": {
|
| 174 |
+
"content": "<img_00018>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"32019": {
|
| 182 |
+
"content": "<img_00019>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": true,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"32020": {
|
| 190 |
+
"content": "<img_00020>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": true,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"32021": {
|
| 198 |
+
"content": "<img_00021>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": true,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"32022": {
|
| 206 |
+
"content": "<img_00022>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": true,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"32023": {
|
| 214 |
+
"content": "<img_00023>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": true,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"32024": {
|
| 222 |
+
"content": "<img_00024>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": true,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"32025": {
|
| 230 |
+
"content": "<img_00025>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": true,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"32026": {
|
| 238 |
+
"content": "<img_00026>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": true,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"32027": {
|
| 246 |
+
"content": "<img_00027>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": true,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"32028": {
|
| 254 |
+
"content": "<img_00028>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": true,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"32029": {
|
| 262 |
+
"content": "<img_00029>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": true,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"32030": {
|
| 270 |
+
"content": "<img_00030>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": true,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"32031": {
|
| 278 |
+
"content": "<img_00031>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": true,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"32032": {
|
| 286 |
+
"content": "<img_00032>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": true,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"32033": {
|
| 294 |
+
"content": "<img_00033>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": true,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"32034": {
|
| 302 |
+
"content": "<img_00034>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": true,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"32035": {
|
| 310 |
+
"content": "<img_00035>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": true,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
},
|
| 317 |
+
"32036": {
|
| 318 |
+
"content": "<img_00036>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": true,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": false
|
| 324 |
+
},
|
| 325 |
+
"32037": {
|
| 326 |
+
"content": "<img_00037>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": true,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": false
|
| 332 |
+
},
|
| 333 |
+
"32038": {
|
| 334 |
+
"content": "<img_00038>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": true,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": false
|
| 340 |
+
},
|
| 341 |
+
"32039": {
|
| 342 |
+
"content": "<img_00039>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": true,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": false
|
| 348 |
+
},
|
| 349 |
+
"32040": {
|
| 350 |
+
"content": "<img_00040>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": true,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": false
|
| 356 |
+
},
|
| 357 |
+
"32041": {
|
| 358 |
+
"content": "<img_00041>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": true,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": false
|
| 364 |
+
},
|
| 365 |
+
"32042": {
|
| 366 |
+
"content": "<img_00042>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": true,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": false
|
| 372 |
+
},
|
| 373 |
+
"32043": {
|
| 374 |
+
"content": "<img_00043>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": true,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": false
|
| 380 |
+
},
|
| 381 |
+
"32044": {
|
| 382 |
+
"content": "<img_00044>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": true,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": false
|
| 388 |
+
},
|
| 389 |
+
"32045": {
|
| 390 |
+
"content": "<img_00045>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": true,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": false
|
| 396 |
+
},
|
| 397 |
+
"32046": {
|
| 398 |
+
"content": "<img_00046>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": true,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": false
|
| 404 |
+
},
|
| 405 |
+
"32047": {
|
| 406 |
+
"content": "<img_00047>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": true,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": false
|
| 412 |
+
},
|
| 413 |
+
"32048": {
|
| 414 |
+
"content": "<img_00048>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": true,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": false
|
| 420 |
+
},
|
| 421 |
+
"32049": {
|
| 422 |
+
"content": "<img_00049>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": true,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": false
|
| 428 |
+
},
|
| 429 |
+
"32050": {
|
| 430 |
+
"content": "<img_00050>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": true,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": false
|
| 436 |
+
},
|
| 437 |
+
"32051": {
|
| 438 |
+
"content": "<img_00051>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": true,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": false
|
| 444 |
+
},
|
| 445 |
+
"32052": {
|
| 446 |
+
"content": "<img_00052>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": true,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": false
|
| 452 |
+
},
|
| 453 |
+
"32053": {
|
| 454 |
+
"content": "<img_00053>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": true,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": false
|
| 460 |
+
},
|
| 461 |
+
"32054": {
|
| 462 |
+
"content": "<img_00054>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": true,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": false
|
| 468 |
+
},
|
| 469 |
+
"32055": {
|
| 470 |
+
"content": "<img_00055>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": true,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": false
|
| 476 |
+
},
|
| 477 |
+
"32056": {
|
| 478 |
+
"content": "<img_00056>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": true,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": false
|
| 484 |
+
},
|
| 485 |
+
"32057": {
|
| 486 |
+
"content": "<img_00057>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": true,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": false
|
| 492 |
+
},
|
| 493 |
+
"32058": {
|
| 494 |
+
"content": "<img_00058>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": true,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
},
|
| 501 |
+
"32059": {
|
| 502 |
+
"content": "<img_00059>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": true,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": false
|
| 508 |
+
},
|
| 509 |
+
"32060": {
|
| 510 |
+
"content": "<img_00060>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": true,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": false
|
| 516 |
+
},
|
| 517 |
+
"32061": {
|
| 518 |
+
"content": "<img_00061>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": true,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": false
|
| 524 |
+
},
|
| 525 |
+
"32062": {
|
| 526 |
+
"content": "<img_00062>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": true,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": false
|
| 532 |
+
},
|
| 533 |
+
"32063": {
|
| 534 |
+
"content": "<img_00063>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": true,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": false
|
| 540 |
+
},
|
| 541 |
+
"32064": {
|
| 542 |
+
"content": "<img>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": true
|
| 548 |
+
},
|
| 549 |
+
"32065": {
|
| 550 |
+
"content": "</img>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": true
|
| 556 |
+
}
|
| 557 |
+
},
|
| 558 |
+
"additional_special_tokens": [
|
| 559 |
+
"<img>",
|
| 560 |
+
"</img>"
|
| 561 |
+
],
|
| 562 |
+
"bos_token": "<s>",
|
| 563 |
+
"clean_up_tokenization_spaces": false,
|
| 564 |
+
"eos_token": "</s>",
|
| 565 |
+
"legacy": false,
|
| 566 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 567 |
+
"pad_token": "<unk>",
|
| 568 |
+
"sp_model_kwargs": {},
|
| 569 |
+
"spaces_between_special_tokens": false,
|
| 570 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 571 |
+
"unk_token": "<unk>",
|
| 572 |
+
"use_default_system_prompt": false
|
| 573 |
+
}
|
detokenizer/detokenizer_george_adapted/checkpoint-4000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:785d4e670ccfdce33b493d0aada60ee5c116918468098b2ed82ae2c28f31e423
|
| 3 |
+
size 6471628187
|
detokenizer/detokenizer_pretrained/checkpoint-55000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da08ec658b25dc40f348bd7e4749e0ad86051e4573469c69991df287a629d46b
|
| 3 |
+
size 2427381181
|
seed_story/george_sft/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46db6f1beb672085204ca9f7d542f6b62063cbe9970933ca702bccc72f00a4f6
|
| 3 |
+
size 14709979626
|
seedx/checkpoint-30000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75d08fcf0c832b02db585ffe6e50e2cceefd9a75e45506b2b5d667c8be9c29c6
|
| 3 |
+
size 14709979626
|