Upload 7 files
Browse files- README.md +9 -0
- gitattributes.txt +33 -0
- merges.txt +0 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
datasets: daspartho/stable-diffusion-prompts
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# Prompt Tokenizer
|
| 8 |
+
|
| 9 |
+
GPT-2 Tokenizer trained on [dataset](https://huggingface.co/datasets/daspartho/stable-diffusion-prompts) of stable diffusion prompts.
|
gitattributes.txt
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 1024,
|
| 6 |
+
"name_or_path": "gpt2",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|