gmonsoon commited on
Commit
56ef469
·
verified ·
1 Parent(s): ab926f0

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -6
app.py CHANGED
@@ -8,13 +8,11 @@ import torch
8
  from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
9
 
10
  DESCRIPTION = """\
11
- # Gemma 2 9B IT
12
 
13
- Gemma 2 is Google's latest iteration of open LLMs.
14
- This is a demo of [`google/gemma-2-9b-it`](https://huggingface.co/google/gemma-2-9b-it), fine-tuned for instruction following.
15
- For more details, please check [our post](https://huggingface.co/blog/gemma2).
16
 
17
- 👉 Looking for a larger and more powerful version? Try the 27B version in [HuggingChat](https://huggingface.co/chat/models/google/gemma-2-27b-it).
18
  """
19
 
20
  MAX_MAX_NEW_TOKENS = 2048
@@ -23,7 +21,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
23
 
24
  device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
25
 
26
- model_id = "google/gemma-2-9b-it"
27
  tokenizer = AutoTokenizer.from_pretrained(model_id)
28
  model = AutoModelForCausalLM.from_pretrained(
29
  model_id,
 
8
  from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
9
 
10
  DESCRIPTION = """\
11
+ # Sahabat-AI
12
 
13
+ Sahabat-AI (Indonesian language for “close friends”) is a collection of Large Language Models (LLMs) which has been pretrained and instruct-tuned for Indonesian language and its various dialects. Sahabat-AI ecosystem is co-initiated by Indonesian tech and telecommunication companies: GoTo Group and Indosat Ooredoo Hutchison.
 
 
14
 
15
+ Gemma2 9B CPT Sahabat-AI v1 Instruct is an Indonesian-focused model which has been fine-tuned with around 448,000 Indonesian instruction-completion pairs alongside an Indonesian-dialect pool consisting of 96,000 instruction-completion pairs in Javanese and 98,000 instruction-completion pairs in Sundanese. Additionally, we added a pool of 129,000 instruction-completion pairs in English.
16
  """
17
 
18
  MAX_MAX_NEW_TOKENS = 2048
 
21
 
22
  device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
23
 
24
+ model_id = "GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct"
25
  tokenizer = AutoTokenizer.from_pretrained(model_id)
26
  model = AutoModelForCausalLM.from_pretrained(
27
  model_id,