166 lines
2.9 KiB
Markdown
166 lines
2.9 KiB
Markdown
---
|
||
license: apache-2.0
|
||
license_name: qwen-research
|
||
license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
|
||
language:
|
||
- en
|
||
pipeline_tag: text-generation
|
||
base_model: Qwen/Qwen2.5-3B-Instruct
|
||
library_name: transformers
|
||
tags:
|
||
- chat
|
||
- instruct
|
||
- assistant
|
||
---
|
||
|
||
# LeeChan-3B-Instruct
|
||
|
||
> **Developed by LeeChanRX Studio**
|
||
|
||
LeeChan-3B-Instruct is a customized conversational AI model developed by **LeeChanRX Studio**. It is designed for chat, coding, reasoning, writing, mathematics, translation, and general-purpose AI assistance.
|
||
|
||
## ✨ Features
|
||
|
||
- 🤖 Intelligent AI Assistant
|
||
- 💻 Code Generation & Debugging
|
||
- 🧠 Advanced Reasoning
|
||
- 📚 Question Answering
|
||
- ✍️ Content Writing
|
||
- 🌍 Multilingual Support
|
||
- 📄 JSON & Structured Output
|
||
- ⚡ GGUF Optimized
|
||
- 📝 Long Context Conversations
|
||
|
||
---
|
||
|
||
## 📊 Model Information
|
||
|
||
| Property | Value |
|
||
|----------|-------|
|
||
| Model Name | LeeChan-3B-Instruct |
|
||
| Developer | LeeChanRX Studio |
|
||
| Parameters | 3.09 Billion |
|
||
| Architecture | Transformer |
|
||
| Context Length | 32,768 Tokens |
|
||
| Max Generation | 8,192 Tokens |
|
||
| Format | Hugging Face Transformers |
|
||
|
||
---
|
||
|
||
## 🚀 Usage
|
||
|
||
### Python (Transformers)
|
||
|
||
```python
|
||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
import torch
|
||
|
||
model_name = "LeeChanRX/LeeChan-3B-Instruct"
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
model = AutoModelForCausalLM.from_pretrained(
|
||
model_name,
|
||
device_map="auto",
|
||
torch_dtype="auto"
|
||
)
|
||
|
||
messages = [
|
||
{
|
||
"role": "system",
|
||
"content": "You are LeeChan-3B-Instruct, developed by LeeChanRX Studio."
|
||
},
|
||
{
|
||
"role": "user",
|
||
"content": "Hello! Introduce yourself."
|
||
}
|
||
]
|
||
|
||
text = tokenizer.apply_chat_template(
|
||
messages,
|
||
tokenize=False,
|
||
add_generation_prompt=True
|
||
)
|
||
|
||
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
||
|
||
outputs = model.generate(
|
||
**inputs,
|
||
max_new_tokens=512,
|
||
temperature=0.7,
|
||
top_p=0.9
|
||
)
|
||
|
||
response = tokenizer.decode(
|
||
outputs[0][inputs.input_ids.shape[-1]:],
|
||
skip_special_tokens=True
|
||
)
|
||
|
||
print(response)
|
||
```
|
||
|
||
---
|
||
|
||
## ⚙️ Recommended Settings
|
||
|
||
| Parameter | Value |
|
||
|-----------|------:|
|
||
| Temperature | 0.7 |
|
||
| Top-p | 0.9 |
|
||
| Top-k | 40 |
|
||
| Repeat Penalty | 1.1 |
|
||
| Max Tokens | 2048–8192 |
|
||
|
||
---
|
||
|
||
## 📦 Installation
|
||
|
||
```bash
|
||
pip install -U transformers accelerate torch sentencepiece
|
||
```
|
||
|
||
---
|
||
|
||
## 🧪 Example
|
||
|
||
**Prompt**
|
||
|
||
```text
|
||
Write a Python function to calculate factorial.
|
||
```
|
||
|
||
**Response**
|
||
|
||
```python
|
||
def factorial(n):
|
||
if n <= 1:
|
||
return 1
|
||
return n * factorial(n - 1)
|
||
```
|
||
|
||
---
|
||
|
||
## 📜 License
|
||
|
||
This project is distributed under the original license applicable to the base model.
|
||
|
||
For complete license information, see:
|
||
|
||
https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
|
||
|
||
---
|
||
|
||
## 👨💻 Developer
|
||
|
||
**LeeChanRX Studio**
|
||
|
||
Building lightweight, efficient, and open AI assistants.
|
||
|
||
---
|
||
|
||
## 📌 Version
|
||
|
||
**LeeChan-3B-Instruct v1.0.0**
|
||
|
||
---
|
||
|
||
© 2026 LeeChanRX Studio. |