dsfsi/tiny_aya_global-lora-r64-nso-eng

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel
import torch

# Configure 4-bit quantization (recommended for memory efficiency)
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_use_double_quant=True,
)

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "CohereLabs/tiny-aya-global",
    quantization_config=bnb_config,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-global")

# Load LoRA adapter
adapter_name = "dsfsi/tiny_aya_global-lora-r64-nso-eng"
model = PeftModel.from_pretrained(base_model, adapter_name)
model.eval()

# Prepare translation prompt
source_text = "Climate change significantly impacts agricultural productivity in sub-Saharan Africa."
instruction = "Translate the following Northern Sotho scientific text to English."

# Format prompt
prompt = f"""### Instruction:
{instruction}

### Input:
{source_text}

### Response:
"""

# Generate translation
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=256,
        num_beams=5,
        early_stopping=True,
        pad_token_id=tokenizer.pad_token_id,
    )

# Decode only the generated part
generated = outputs[0][inputs["input_ids"].shape[1]:]
translation = tokenizer.decode(generated, skip_special_tokens=True)
print(translation)

# For GPUs with sufficient memory (>24GB for larger models)
base_model = AutoModelForCausalLM.from_pretrained(
    "CohereLabs/tiny-aya-global",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
model = PeftModel.from_pretrained(base_model, "dsfsi/tiny_aya_global-lora-r64-nso-eng")

# Clone the AfriScience-MT repository
git clone https://github.com/afriscience-mt/afriscience-mt.git
cd afriscience-mt

# Install dependencies
pip install -r requirements.txt

# Run LoRA training
python -m afriscience_mt.scripts.run_lora_training \
    --data_dir ./data \
    --source_lang nso \
    --target_lang eng \
    --model_name CohereLabs/tiny-aya-global \
    --model_type causal \
    --lora_rank 64 \
    --output_dir ./output \
    --num_epochs 3 \
    --batch_size 4 \
    --load_in_4bit

@article{abdulmumin2026afriscience,
  title   = {AfriScience-MT: Towards Decolonizing Science in Africa through Text Translation},
  author  = {Abdulmumin, Idris and Gwadabe, Tajuddeen and Muhammad, Shamsuddeen Hassan and Adelani, David Ifeoluwa and Khalo, Nomonde and Ahmad, Ibrahim Said and Modupe, Abiodun and Mumm, Anina and Biyela, Sibusiso and Rabie, Michelle and Havemann, Johanna and Rei, Marek and Abbott, Jade and Marivate, Vukosi},
  journal = {arXiv preprint arXiv:2605.29741},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.29741}
}