hieunguyen1053
commited on
Commit
•
a623f0f
1
Parent(s):
3fe7c65
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: bigscience-bloom-rail-1.0
|
3 |
+
language:
|
4 |
+
- vi
|
5 |
+
- en
|
6 |
+
library_name: transformers
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
tags:
|
9 |
+
- bloom
|
10 |
+
- causal-lm
|
11 |
+
- pytorch
|
12 |
+
---
|
13 |
+
|
14 |
+
# Hoa 1B4 (Bloom architecture)
|
15 |
+
|
16 |
+
Hoa is an autoregressive Large Language Model (LLM), based on Bloom's model architecture.
|
17 |
+
Hoa was trained on part of the Common Crawl dataset in Vietnamese and English.
|
18 |
+
|
19 |
+
Details will be available soon.
|
20 |
+
|
21 |
+
To contact us, mail to: leanhcuong@gmail.com (Lê Anh Cường) | hieunguyen1053@outlook.com (Hiếu)
|
22 |
+
|
23 |
+
### How to use
|
24 |
+
```python
|
25 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
26 |
+
|
27 |
+
tokenizer = AutoTokenizer.from_pretrained("vlsp-2023-vllm/hoa-1b4")
|
28 |
+
model = AutoModelForCausalLM.from_pretrained("vlsp-2023-vllm/hoa-1b4", low_cpu_mem_usage=True)
|
29 |
+
|
30 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
31 |
+
model.to(device)
|
32 |
+
|
33 |
+
prompt = "Địa chỉ trường Đại học Tôn Đức Thắng nằm ở số"
|
34 |
+
input_ids = tokenizer(prompt, return_tensors="pt")['input_ids'].to(device)
|
35 |
+
|
36 |
+
gen_tokens = model.generate(input_ids, max_length=max_length, repetition_penalty=1.1)
|
37 |
+
|
38 |
+
print(tokenizer.batch_decode(gen_tokens)[0])
|
39 |
+
```
|