|
|
--- |
|
|
base_model: |
|
|
- google/flan-t5-large |
|
|
license: apache-2.0 |
|
|
metrics: |
|
|
- bleu |
|
|
tags: |
|
|
- code |
|
|
language: |
|
|
- en |
|
|
new_version: google/flan-t5-large |
|
|
pipeline_tag: graph-ml |
|
|
datasets: |
|
|
- none-yet/anime-captions |
|
|
library_name: pyannote-audio |
|
|
--- |
|
|
### 📦 Model Weights Usage |
|
|
|
|
|
This repository hosts two separate model weights that need to be used together for the full functionality of Style2Code: |
|
|
|
|
|
✅ **Style Encoder Checkpoint (first stage)**: |
|
|
Trained via contrastive learning to extract explicit style embeddings. |
|
|
|
|
|
✅ **Flan-T5 Generator Checkpoint (second stage)**: |
|
|
Fine-tuned to generate code while incorporating the style embeddings. |
|
|
|
|
|
To **use these weights**: |
|
|
|
|
|
1️⃣ Clone the Style2Code repository: |
|
|
```bash |
|
|
git clone https://github.com/zh19980811/Style2Code.git |
|
|
cd Style2Code |
|
|
|
