Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,8 @@ language:
|
|
| 12 |
- en
|
| 13 |
library_name: transformers
|
| 14 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
## Model description
|
|
@@ -22,7 +24,7 @@ It is trained on the raw tags of danbooru with underscores and spaces. Only post
|
|
| 22 |
|
| 23 |
# Training
|
| 24 |
|
| 25 |
-
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on a dataset of the tags of 118k random posts of danbooru.donmai.us .
|
| 26 |
It achieves the following results on the evaluation set:
|
| 27 |
- Loss: 3.6934
|
| 28 |
- Accuracy: 0.4650
|
|
@@ -71,4 +73,4 @@ OpenAI states in the GPT-2 [model card](https://github.com/openai/gpt-2/blob/mas
|
|
| 71 |
- Transformers 4.27.0.dev0
|
| 72 |
- Pytorch 1.13.1+cu116
|
| 73 |
- Datasets 2.9.0
|
| 74 |
-
- Tokenizers 0.13.2
|
|
|
|
| 12 |
- en
|
| 13 |
library_name: transformers
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
+
datasets:
|
| 16 |
+
- 0Tick/Danbooru-Random-Posts-Scrape
|
| 17 |
---
|
| 18 |
|
| 19 |
## Model description
|
|
|
|
| 24 |
|
| 25 |
# Training
|
| 26 |
|
| 27 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on a dataset of the tags of 118k random posts of (danbooru)[danbooru.donmai.us] .
|
| 28 |
It achieves the following results on the evaluation set:
|
| 29 |
- Loss: 3.6934
|
| 30 |
- Accuracy: 0.4650
|
|
|
|
| 73 |
- Transformers 4.27.0.dev0
|
| 74 |
- Pytorch 1.13.1+cu116
|
| 75 |
- Datasets 2.9.0
|
| 76 |
+
- Tokenizers 0.13.2
|