Build with OribAI

pip install transformers torch accelerate

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Alkamal01/oribai-14b-hausa-yoruba-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "system", "content": "You are OribAI, a helpful Hausa and Yoruba assistant."},
    {"role": "user", "content": "Menene babban birnin Nijeriya?"}
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
output = model.generate(input_ids, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))
# >>> Abuja

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "Alkamal01/oribai-14b-hausa-yoruba-v1",
    load_in_4bit=True   # 4-bit quantization for low VRAM
)
FastLanguageModel.for_inference(model)

# Generate
inputs = tokenizer(
    [tokenizer.apply_chat_template(
        [{"role": "user", "content": "Ṣe alaye ìtàn Yoruba fún mi."}],
        tokenize=False, add_generation_prompt=True
    )], return_tensors="pt"
).to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

# llama.cpp — download GGUF from HuggingFace, then:
./llama-cli -m oribai-14b-q4_k_m.gguf \
  -p "Menene babban birnin Nijeriya?" \
  --temp 0.7 --top-p 0.9

# Ollama (from local GGUF)
# Create a Modelfile with: FROM ./oribai-14b-q4_k_m.gguf
ollama create oribai -f Modelfile
ollama run oribai