ChindaMT-4B

ChindaMT-4B is an open-weight Thai-English machine translation model fine-tuned from Qwen/Qwen3.5-4B. It supports plain translation and instruction-following translation with auxiliary rules in the prompt.

• Task: Thai-English machine translation with instruction-following
• Base model: Qwen3.5-4B
• Parameter count: 4B
• License: Apache-2.0

Prompting

Plain translation. Same template for both directions; swap the language line and the source-tag:

Translate English to Thai.

EN: The weather is nice today.

Translate Thai to English.

TH: วันนี้อากาศดีมาก

With instruction following. Add a Rules: block between the language line and the source line. Rules are free-form text:

Translate English to Thai.
Rules:
- Return only the translated text
- Use a clear, professional tone in Thai
- Keep all numerals in Arabic digits

EN: <source text>

Inference

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "iapp/ChindaMT-4B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)

prompt = "Translate English to Thai.\n\nEN: The weather is nice today."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(
    **inputs, max_new_tokens=1024, temperature=0.01, top_p=0.7, top_k=20,
    repetition_penalty=1.05, do_sample=True,
)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Evaluation datasets

The evaluation suites used during development will be released soon:

• iapp/ChindaMT-CoreEval: 5-domain primary evaluation
• iapp/ChindaMT-BroadEval: 10-domain generalization check

Limitations

• Thai-English only.
• Behavior on out-of-domain or paragraph-length inputs is not comprehensively characterized.

iApp AI Research