Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- vi
|
4 |
+
tags:
|
5 |
+
- text generation
|
6 |
+
- pytorch
|
7 |
+
- the Pile
|
8 |
+
- causal-lm
|
9 |
+
# GPT-Neo-small for vietnamese
|
10 |
+
## Model Description
|
11 |
+
GPT-Neo-vi-small is a transformer model designed using EleutherAI's replication of the GPT-3 architecture.
|
12 |
+
## Training data
|
13 |
+
GPT-Neo-vi-smal was trained on the News datasets, a large scale dataset created by from News Website for the purpose of training this model.
|
14 |
+
### How to use
|
15 |
+
his example generates a different sequence each time it's run:
|
16 |
+
```py
|
17 |
+
from transformers import GPTNeoForCausalLM, GPT2Tokenizer
|
18 |
+
model = GPTNeoForCausalLM.from_pretrained("NlpHUST/gpt-neo-vi-small")
|
19 |
+
tokenizer = GPT2Tokenizer.from_pretrained("NlpHUST/gpt-neo-vi-small")
|
20 |
+
|
21 |
+
prompt = "Ngay sau Tết Nguyên đán Tân Sửu, hiện tượng giá đất tăng tại nhiều địa phương. Thị trường nhộn nhịp, tạo ra những cơn sóng sốt đất khó tin khiến bộ ngành, địa phương đưa cảnh báo."
|
22 |
+
|
23 |
+
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
|
24 |
+
gen_tokens = model.generate(input_ids, do_sample=True, temperature=1.0, max_length=1024)
|
25 |
+
gen_text = tokenizer.batch_decode(gen_tokens)[0]
|
26 |
+
print(gen_text)
|
27 |
+
|
28 |
+
|
29 |
+
|
30 |
+
```
|