Instructions to use MaAIos/Liyama-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MaAIos/Liyama-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MaAIos/Liyama-3B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MaAIos/Liyama-3B") model = AutoModelForCausalLM.from_pretrained("MaAIos/Liyama-3B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MaAIos/Liyama-3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MaAIos/Liyama-3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MaAIos/Liyama-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/MaAIos/Liyama-3B
- SGLang
How to use MaAIos/Liyama-3B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "MaAIos/Liyama-3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MaAIos/Liyama-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "MaAIos/Liyama-3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MaAIos/Liyama-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use MaAIos/Liyama-3B with Docker Model Runner:
docker model run hf.co/MaAIos/Liyama-3B
π¦ Liyama-3B
Liyama-3B is a fine-tuned version of Metaβs LLaMA-3B (3.2) model, built to understand and respond fluently in Tagalog. It was trained on the AnoNa dataset over 3 epochs, aiming for natural, context-aware instruction-following in Filipino.
π€ Origin of the Name
The name Liyama is a Tagalified version of llama, reflecting both its LLaMA base and its Tagalog-focused language capabilities. It mirrors how Filipino often adapts foreign terms into familiar, phonetic formsβlike camera β kamera, lion β leon, and now, llama β liyama.
π§ Training Data: The AnoNa Dataset
Liyama-3B was trained solely on response completions from the AnoNa dataset β a self-instruct corpus generated using Gemini 1.5 and 2.0.
Inspired by SimpleQnA, the dataset contains short, helpful instruction-response pairs. But AnoNa introduces several improvements:
- β Less English, More Tagalog prompts
- β Less IFEVAL-style formatting
- β No overuse of modifiers in instructions
- β Balanced task types to avoid dominant categories
- β Complex tasks favored (65% complex / 35% simple)
- β Reduced sycophancy and generic praise
- β Improved follow-up handling
- β AI self-intro appears only when relevant
- β Implicit chain-of-thought reasoning, not labeled
- β Extra task types added to increase variety
This focus creates a model that's practical, straightforward, and tuned for realistic conversational use in Filipino, without excessive formatting or irrelevant disclaimers.
π£οΈ Use Case
Liyama-3B is ideal for:
- Answering questions in Tagalog
- Writing essays, reflections, and letters in Filipino
- Following natural instructions, even when mixed with English
- Chat-based tasks where fluency and tone matter
- Educational or community apps centered around local language use
π¦ Model Details
| Feature | Value |
|---|---|
| Base Model | LLaMA-3B v3.2 |
| Fine-tuned Dataset | AnoNa |
| Epochs | 3 |
| Language Focus | Tagalog (with some English) |
| Prompt Format | Responses only |
Liyama-3B is part of a broader effort to create open, practical Filipino-language models for real useβnot just benchmarks. Expect follow-ups tuned for multi-turn chat, reasoning, and creative tasks.
- Downloads last month
- 8