Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

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")
Downloads last month
6
Safetensors
Model size
8.54B params
Tensor type
F32
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using AingHongsin/SurMuy_v1_512512201 1