OPUS-100 EN↔VI parallel pairs (filtered)
Synthetic customer support instruction examples (order status, refunds, shipping delays, account issues, billing)
Final split: 176k train / 4k eval

Training setup

Framework: Unsloth + TRL SFTTrainer
Precision: bf16
Quantization for training: 4-bit base model
LoRA: r=32, alpha=64, dropout=0.0
Max seq len: 768

Prompt format

text

Instruction:
{instruction}

User:
{input}

Assistant:

Quick usage (PEFT)

python

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

base = "Qwen/Qwen2.5-3B-Instruct"
adapter = "REPLACE_WITH_HF_REPO"

tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)

prompt = """Instruction:
Bạn là nhân viên chăm sóc khách hàng tiếng Việt. Trả lời lịch sự, đồng cảm, và nêu bước tiếp theo rõ ràng.

User:
Xin chào, đơn hàng của tôi bị trễ 5 ngày. Mã đơn #A12345.

Assistant:
"""

inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=180, temperature=0.3, do_sample=True)
print(tok.decode(out[0], skip_special_tokens=True))

Limitations

Not a legal/compliance authority
Can still hallucinate policy details if product policy is ambiguous
Should be paired with retrieval or hard policy checks in production

Recommended production guardrails

Ground responses on your real policy KB
Enforce redaction/PII handling
Add escalation rules for sensitive requests

vochris/viet-customer-support-model

qwen2.5-3b-viet-customer-support-lora

What this model is for

Base model

Training data (high-level)

Training setup

Prompt format

Quick usage (PEFT)

Limitations

Recommended production guardrails

vochris/
viet-customer-support-model