Dqdung205's picture
Update README.md
603924c verified
---
language: vi
library_name: transformers
pipeline_tag: text-generation
tags:
- unsloth
- qwen
- function-calling
- vietnamese
- finetuned
- chatml
license: mit
---
# 🧠 Qwen Function-Calling (Vietnamese Finetune)
Model này là một phiên bản **Qwen-based model** được **finetune bằng [Unsloth](https://github.com/unslothai/unsloth)**
trên dữ liệu hội thoại tiếng Việt có khả năng **function-calling** từ bộ dữ liệu:
👉 [`5CD-AI/Vietnamese-Locutusque-function-calling-chatml-gg-translated`](https://huggingface.co/datasets/5CD-AI/Vietnamese-Locutusque-function-calling-chatml-gg-translated)
---
## 🧩 Model Details
- **Base model:** Qwen/Qwen2.5-7B-Instruct
- **Finetuning framework:** [Unsloth](https://github.com/unslothai/unsloth)
- **Task:** Text Generation + Function Calling
- **Language:** Vietnamese 🇻🇳
- **Architecture:** Decoder-only Transformer (Causal LM)
- **License:** MIT
- **Finetuned from:** Qwen base model
---
## 🚀 How to Use
### Inference Example (Transformers)
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "dungai/qwen-function-calling"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
prompt = "Xin chào! Hãy gọi hàm `get_weather` với tham số thành phố là Hà Nội."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))