Bahasa 4b Chat

🚀 Bahasa-4b Model Report

Bahasa-4b is a model fine - tuned from Qwen - 4b, trained on high - quality Indonesian text. It shows excellent performance in various Indonesian NLP tasks.

🚀 Quick Start

If you want to use the Bahasa-4b model, you can refer to the following code example:

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "Bahasalab/Bahasa-4b-chat-v2",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Bahasalab/Bahasa-4b-chat")

messages = [
    {"role": "system", "content": "Kamu adalah asisten yang membantu"},
    {"role": "user", "content": "kamu siapa"}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    input_ids=model_inputs.input_ids,
    attention_mask=model_inputs.attention_mask,
    max_new_tokens=512,
    eos_token_id=tokenizer.eos_token_id

)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

✨ Features

• Bahasa-4b is continued training from qwen-4b using 10 billion high quality text of Indonesian.
• The model outperforms some 4b, and even 7b models for Indonesian tasks.
• It is suitable for various NLP tasks that require understanding and generating Indonesian language, such as question answering, sentiment analysis, document summarization, etc.

📚 Documentation

Model Name

Bahasa-4b

Model Developers

Bahasa AI

Intended Use

This model is intended for various NLP tasks that require understanding and generating Indonesian language. It is suitable for applications such as question answering, sentiment analysis, document summarization, and more.

Training Data

Bahasa-4b was trained on a 10 billion subset data of Indonesian dataset from a collected pool of 100 billion.

Benchmarks

The following table shows the performance of Bahasa-4b compared to the models Sailor_4b and Mistral-7B-v0.1 across several benchmarks:

This data demonstrates that Bahasa-4b consistently outperforms the Sailor_4b model in various Indonesian language tasks, showing improvements in both EM (Exact Match) and F1 scores across different datasets, and is competitive with the Mistral-7B-v0.1 model.

📄 License

The license of this model is "other", named "tongyi - qianwen".