SHERWYNLUCIAN commited on
Commit
9e93c16
·
verified ·
1 Parent(s): 4518f89

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +46 -13
README.md CHANGED
@@ -1,21 +1,54 @@
1
  ---
2
- base_model: unsloth/qwen2.5-3b-instruct-bnb-4bit
 
3
  tags:
4
- - text-generation-inference
5
- - transformers
6
  - unsloth
7
- - qwen2
8
- license: apache-2.0
9
- language:
10
- - en
 
11
  ---
12
 
13
- # Uploaded finetuned model
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
 
15
- - **Developed by:** SHERWYNLUCIAN
16
- - **License:** apache-2.0
17
- - **Finetuned from model :** unsloth/qwen2.5-3b-instruct-bnb-4bit
 
 
18
 
19
- This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
20
 
21
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
4
  tags:
 
 
5
  - unsloth
6
+ - qwen
7
+ - text-generation
8
+ - vietnamese
9
+ - code-assistant
10
+ - evonet
11
  ---
12
 
13
+ # 🧬 EvoNet-3B-v0.2 (Full Base)
14
+
15
+ **EvoNet-3B-v0.2** is a specialized language model optimized for **Vietnamese language understanding** and **Coding tasks**. Built upon the robust Qwen 2.5 architecture, this model has been fine-tuned to provide concise, accurate, and safe responses.
16
+
17
+ **EvoNet-3B-v0.2** là mô hình ngôn ngữ chuyên biệt được tối ưu hóa cho **Tiếng Việt** và **Lập trình**. Được xây dựng trên nền tảng Qwen 2.5, mô hình được tinh chỉnh để đưa ra câu trả lời ngắn gọn, chính xác và an toàn.
18
+
19
+ ## 👨‍💻 Author / Tác giả
20
+ - **Developer:** Founder Huỳnh Dương Phong
21
+ - **Architecture:** Qwen 2.5 (3B Parameters)
22
+ - **Fine-tuned with:** Unsloth & TRL
23
+
24
+ ## 🚀 Key Features / Tính năng nổi bật
25
+ - **Lightweight / Nhẹ:** ~3 Billion parameters, runnable on consumer GPUs (T4, RTX 3060...).
26
+ - **Vietnamese Optimized / Tối ưu Tiếng Việt:** Natural language processing for Vietnamese contexts.
27
+ - **Coding Expert / Chuyên gia Code:** Enhanced capability in Python, JavaScript, and debugging.
28
+
29
+ ## 📥 How to Use (Python)
30
+
31
+ ```python
32
+ from transformers import AutoModelForCausalLM, AutoTokenizer
33
+ import torch
34
+
35
+ model_name = "SHERWYNLUCIAN/EvoNet-3B-v0.2-FullBase"
36
+
37
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
38
+ model = AutoModelForCausalLM.from_pretrained(
39
+ model_name,
40
+ torch_dtype=torch.float16,
41
+ device_map="auto"
42
+ )
43
 
44
+ # Chat Template (ChatML)
45
+ messages = [
46
+ {"role": "system", "content": "Bạn EvoNet, trợ lý AI thông minh chuyên về lập trình."},
47
+ {"role": "user", "content": "Viết hàm Python tính tổng 2 số."}
48
+ ]
49
 
50
+ text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
51
+ inputs = tokenizer(text, return_tensors="pt").to("cuda")
52
 
53
+ outputs = model.generate(**inputs, max_new_tokens=512)
54
+ print(tokenizer.decode(outputs[0], skip_special_tokens=True))