71 lines
1.7 KiB
Markdown
71 lines
1.7 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- vi
|
||
|
|
pretty_name: Chatbot IELTS Assistant v2
|
||
|
|
license: apache-2.0
|
||
|
|
tags:
|
||
|
|
- qwen3
|
||
|
|
- chatbot
|
||
|
|
- conversational
|
||
|
|
- ielts
|
||
|
|
- education
|
||
|
|
- text-generation
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen3-4B-Instruct-2507
|
||
|
|
---
|
||
|
|
|
||
|
|
# 📘 Chatbot IELTS Assistant v2
|
||
|
|
|
||
|
|
**Chatbot IELTS Assistant v2** is a fine-tuned conversational language model built on **Qwen3-4B-2507**, designed to assist learners preparing for the **IELTS exam**.
|
||
|
|
It provides natural dialogue responses and helpful explanations for Speaking, Writing, Reading, Listening, vocabulary, and grammar.
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## 📌 Model Summary
|
||
|
|
|
||
|
|
| Attribute | Value |
|
||
|
|
|------------------|-------|
|
||
|
|
| **Model type** | Conversational LLM |
|
||
|
|
| **Base model** | Qwen3-4B-2507 |
|
||
|
|
| **Training** | Fine-tuned for IELTS-related dialogue |
|
||
|
|
| **Languages** | English, Vietnamese |
|
||
|
|
| **License** | Apache-2.0 |
|
||
|
|
| **Intended use** | IELTS learning assistant |
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## 🎯 Intended Use Cases
|
||
|
|
|
||
|
|
This model is suitable for:
|
||
|
|
|
||
|
|
- IELTS Speaking practice
|
||
|
|
- IELTS Writing task explanations
|
||
|
|
- Vocabulary & grammar guidance
|
||
|
|
- English learning conversation
|
||
|
|
- General educational Q&A
|
||
|
|
|
||
|
|
**NOT recommended for:**
|
||
|
|
|
||
|
|
- Legal, medical, financial advice
|
||
|
|
- High-risk decision making
|
||
|
|
- Producing official IELTS scores
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
## 🚀 How to Use
|
||
|
|
|
||
|
|
### Python (Transformers)
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
|
||
|
|
model_name = "Zkare/Chatbot_Ielts_Assistant_v2"
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
||
|
|
|
||
|
|
prompt = "Help me practice IELTS Speaking Part 2."
|
||
|
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||
|
|
outputs = model.generate(**inputs, max_new_tokens=180)
|
||
|
|
|
||
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|