Instructions to use JakeOh/LLaDA-Tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JakeOh/LLaDA-Tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="JakeOh/LLaDA-Tiny", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JakeOh/LLaDA-Tiny", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- char_tokenizer.py +3 -0
char_tokenizer.py
CHANGED
|
@@ -15,6 +15,9 @@ class CharTokenizer(PreTrainedTokenizer):
|
|
| 15 |
Compatible with HuggingFace transformers.
|
| 16 |
"""
|
| 17 |
|
|
|
|
|
|
|
|
|
|
| 18 |
def __init__(
|
| 19 |
self,
|
| 20 |
vocab_file: Optional[str] = None,
|
|
|
|
| 15 |
Compatible with HuggingFace transformers.
|
| 16 |
"""
|
| 17 |
|
| 18 |
+
# Required for HuggingFace from_pretrained to locate and load vocab file
|
| 19 |
+
vocab_files_names = {"vocab_file": "vocab.json"}
|
| 20 |
+
|
| 21 |
def __init__(
|
| 22 |
self,
|
| 23 |
vocab_file: Optional[str] = None,
|