File size: 1,834 Bytes
e64cbf7 a215b95 e64cbf7 52b6734 a215b95 52b6734 a215b95 52b6734 a215b95 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
---
license: apache-2.0
datasets:
- AiresPucrs/sentiment-analysis
language:
- en
metrics:
- accuracy
library_name: keras
---
# English Embedding v.16 (Teeny-Tiny Castle)
This model is part of a tutorial tied to the [Teeny-Tiny Castle](https://github.com/Nkluge-correa/TeenyTinyCastle), an open-source repository containing educational tools for AI Ethics and Safety research.
## How to Use
```python
import numpy as np
import tensorflow as tf
from huggingface_hub import hf_hub_download
# Download the model
hf_hub_download(repo_id="AiresPucrs/english-embedding-vocabulary-16",
filename="english_embedding_vocabulary_16.keras",
local_dir="./",
repo_type="model"
)
# Download the embedding vocabulary txt file
hf_hub_download(repo_id="AiresPucrs/english-embedding-vocabulary-16",
filename="english_embedding_vocabulary.txt",
local_dir="./",
repo_type="model"
)
model = tf.keras.models.load_model('english_embedding_vocabulary_16.keras')
# Compile the model
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
with open('english_embedding_vocabulary.txt', encoding='utf-8') as fp:
english_embedding_vocabulary = [line.strip() for line in fp]
fp.close()
embeddings = model.get_layer('embedding').get_weights()[0]
words_embeddings = {}
# iterating through the elements of list
for i, word in enumerate(english_embedding_vocabulary):
# here we skip the embedding/token 0 (""), because is just the PAD token.
if i == 0:
continue
words_embeddings[word] = embeddings[i]
print("Embeddings Dimensions: ", np.array(list(words_embeddings.values())).shape)
print("Vocabulary Size: ", len(words_embeddings.keys()))
```
|