Upload model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Word2Vec Model
|
| 2 |
+
|
| 3 |
+
This is a Word2Vec model trained on text data.
|
| 4 |
+
|
| 5 |
+
## Model Details
|
| 6 |
+
- **Vocabulary size**: 3
|
| 7 |
+
- **Embedding dimension**: 64
|
| 8 |
+
- **Total words**: 35174
|
| 9 |
+
|
| 10 |
+
## Usage
|
| 11 |
+
|
| 12 |
+
```python
|
| 13 |
+
from transformers import AutoTokenizer
|
| 14 |
+
import torch
|
| 15 |
+
|
| 16 |
+
# Load tokenizer
|
| 17 |
+
tokenizer = AutoTokenizer.from_pretrained("roshbeed/hn-word2vec")
|
| 18 |
+
|
| 19 |
+
# Load embeddings
|
| 20 |
+
embeddings = torch.load("word_embeddings.pt")
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
## Training Data
|
| 24 |
+
Trained on text8 dataset with synthetic upvote scores.
|