BharatGPT-Embedding

BharatGPT-Embedding is a state-of-the-art multilingual text embedding model developed by the BharatGPT team, designed for Indian languages and English.

Model Highlights

• Optimized for multilingual semantic search
• Supports English, Hindi, Bengali, Telugu, Tamil, Marathi, Gujarati
• Ideal for RAG pipelines, semantic similarity, and document retrieval

How to Use

from transformers import AutoTokenizer, AutoModel
import torch

tokenizer = AutoTokenizer.from_pretrained("harry121/BharatGPT-Embedding")
model = AutoModel.from_pretrained("harry121/BharatGPT-Embedding")

inputs = tokenizer("your text here", return_tensors="pt", padding=True, truncation=True)

with torch.no_grad():
    outputs = model(**inputs)

# Mean pooling
embeddings = outputs.last_hidden_state.mean(dim=1)
print("Embedding shape:", embeddings.shape)

License

Apache 2.0 — free for commercial and personal use.

Contact

BharatGPT Team