Dineochiloane/gemma-3-4b-isizulu-simple

Simple isiZulu→English Translation Model

Simple and focused isiZulu to English translation model using consistent prompting.

Model Details

• Base Model: google/gemma-3-4b-it
• Task: isiZulu → English Translation
• Training Examples: 5000
• Prompt Format: "Translate this from isiZulu to English: [text]"

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Load model
base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it")
tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-4b-it")
model = PeftModel.from_pretrained(base_model, "Dineochiloane/gemma-3-4b-isizulu-simple")

# Translate
messages = [{"role": "user", "content": "Translate this from isiZulu to English: Ngiyabonga kakhulu"}]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt")
outputs = model.generate(input_ids, max_new_tokens=50, repetition_penalty=1.2)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Details

• LoRA Rank: 32
• LoRA Alpha: 32
• Learning Rate: 5e-05
• Epochs: 2
• Consistent Prompting: All training uses same format as evaluation