SHERWYNLUCIAN's picture
Update README.md
ae623c2 verified
---
license: apache-2.0
base_model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
tags:
- unsloth
- loRA
- peft
- vietnamese
- evonet
---
# 🧩 EvoNet-3B-v0.2 (LoRA Adapter)
This repository contains the **LoRA Adapter weights** for EvoNet v0.2.
Đây là file trọng số Adapter (LoRA) của dự án EvoNet v0.2.
**Note:** This is NOT a standalone model. You need the base model to use this.
**Lưu ý:** Đây không phải là model độc lập. Bạn cần model gốc để chạy.
## 👨‍💻 Developer
Founder Huỳnh Dương Phong
## 🔧 Training Details
- **Framework:** Unsloth
- **Base Model:** Qwen 2.5 3B Instruct (4-bit)
- **LoRA Rank (r):** 16
- **LoRA Alpha:** 16
- **Target Modules:** q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
## 📥 Usage with Unsloth
```python
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "EvoNet/EvoNet-3B-v0.2-Stable",
max_seq_length = 2048,
dtype = None,
load_in_4bit = True,
)