afrizalha commited on
Commit
f5efc68
1 Parent(s): ded43e3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -2
README.md CHANGED
@@ -11,9 +11,32 @@ tags:
11
  - trl
12
  - sft
13
  ---
14
- # Open models for indigenous Indonesian languages
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
 
16
- Bakpia 1 is a fine-tuned version of Qwen 2 1.5B Instruct. It is fine-tuned using massive synthetic data for Krama Javanese, where the prompts are generated by GPT-4o and the responses are generated by Claude 3 Haiku.
 
 
 
 
 
17
 
18
  # Version 1.0
19
 
 
11
  - trl
12
  - sft
13
  ---
14
+ <!DOCTYPE html>
15
+ <html lang="en">
16
+ <head>
17
+ <meta charset="UTF-8">
18
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
19
+ <title>Document Title</title>
20
+ <style>
21
+ h1 {
22
+ font-size: 36px;
23
+ color: navy;
24
+ font-family: 'Tahoma';
25
+ text-align: center;
26
+ }
27
+ </style>
28
+ </head>
29
+ <body>
30
+ <h1> Open models for indigenous Indonesian languages</h1>
31
+ </body>
32
+ </html>
33
 
34
+ <center>
35
+ <img src="https://imgur.com/R91sZas.png" alt="Bakpia" width="600" height="300">
36
+ <p><em>Bakpia is a family of open language models capable of responding in Javanese langauge. Version one of Bakpia is the first generative Javanese LLM gain functional instruction performance using solely synthetic data.</em></p>
37
+ <p><em style="color: black; font-weight: bold;">Beta preview</em></p>
38
+ </center>
39
+ Bakpia V1 is a fine-tuned version of Qwen 2 1.5B Instruct. It is fine-tuned using massive synthetic data for Krama Javanese, where the prompts are generated by GPT-4o and the responses are generated by Claude 3 Haiku.
40
 
41
  # Version 1.0
42