SurMuy
Welcome to the repository for SurMuy, SurMuy is a question-answer model fine-tuned from the SeaLLM-7B-V2.5, specifically designed to handle queries in Khmer. By utilizing a specialized dataset of Khmer questions and answers, SurMuy is optimized for high accuracy and contextual relevance in the Cambodian language. This makes it highly effective for educational, customer service, and other interactive applications requiring fluent Khmer language processing.
Model Details
- Model Version: 1.0
- Model Type: Gemma
- Pre-trained on: Decoder-only Transformers
- Fine-tuned for: Chatbot with Khmer Natives language
- Developed by: Aing Hongsin
- Base Model: SeaLLM-7B-v2.5
- Contact: [email protected]
Requirements
- Python 3.12+
- torch 1.10.0+
- transformers 4.4.0+
- optimum>=1.2.0+
- numpy>=1.21.0+
Used
Load this model with transformers
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("AingHongsin/SurMuy_v1_512512201")
model = AutoModelForCausalLM.from_pretrained("AingHongsin/SurMuy_v1_512512201")