Instructions to use hungta/zaic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hungta/zaic with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507") model = PeftModel.from_pretrained(base_model, "hungta/zaic") - Notebooks
- Google Colab
- Kaggle
ZAIC 2026 LifeMate: Qwen3-4B LoRA adapter
LoRA adapter (r=16, alpha=32, 1 epoch, lr 1e-4, seed 42) for Qwen/Qwen3-4B-Instruct-2507, used as a Vietnamese tool-calling agent.
Trained on the LifeMate train split minus a 200-sample dev hold-out, with 50% of user turns replaced by Qwen3-ASR-0.6B transcripts.
| Setup | Input text | Dev score (official metric, 200 samples) |
|---|---|---|
| Qwen3-4B base, prompt + guard + 4-shot | Qwen3-ASR-0.6B | 25.14 |
| Qwen3-4B + this LoRA | PhoWhisper-large | 34.71 |
System budget: Qwen3-4B (4.02B) + PhoWhisper-large (1.55B) = 5.57B parameters.
Serve with vLLM: --enable-lora --lora-modules lifemate=<path> --max-lora-rank 16.
- Downloads last month
- 22
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for hungta/zaic
Base model
Qwen/Qwen3-4B-Instruct-2507