Key1111/vinallama-vietnamese-lora

Fine-tuned VinaLLaMA-7B for Vietnamese language tasks using LoRA.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained("vilm/vinallama-7b-chat")
tokenizer = AutoTokenizer.from_pretrained("vilm/vinallama-7b-chat")

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "Key1111/vinallama-vietnamese-lora")

Training Details

• Base Model: vilm/vinallama-7b-chat
• LoRA Rank: 8
• LoRA Alpha: 16
• Training Data: Alpaca + ViQuAD
• Language: Vietnamese