Orvex/Orvex-Alpha-v1

🤖 Orvex Alpha v1

Orvex Alpha v1 is a high-performance bilingual large language model (LLM) optimized for Sinhala and English. Built with a Mixture of Experts (MoE) architecture, it captures linguistic nuances better than general-purpose global models.

---

🚀 Key Features

• Bilingual Native Support: Expertly handles Sinhala syntax and grammar alongside English.
• MoE Architecture: Uses multiple specialized layers to provide high-quality responses.
• Quantization Ready: Can be run on consumer GPUs using 4-bit or 8-bit quantization.

🛠️ How to Use

To load this 37GB model efficiently, use the following code:

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

model_id = "Orvex/Orvex-Alpha-v1"
bnb_config = BitsAndBytesConfig(load_in_4bit=True)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config)