firobeid/L3_financial_news_headlines_Word2Vec

Custom Word2Vec Embeddings

This model contains custom word embeddings trained using Gensim's Word2Vec implementation.

Model details

• Trained using Gensim's Word2Vec
• Includes custom n-grams as tokens
• Vector size: 100
• Context window: 5
• Training algorithm: Skip-gram

Usage

from transformers import AutoTokenizer, AutoModel
import torch

# Load model directly
from transformers import AutoModel, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("your-username/your-model-name")
model = AutoModel.from_pretrained("your-username/your-model-name")

# Or load from the hub using gensim:
from gensim.models import KeyedVectors
import gensim.downloader as api

# Load vectors directly using gensim
word_vectors = api.load("your-username/your-model-name")