Artples commited on
Commit
ea3f2b3
1 Parent(s): 49fab10

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -9
app.py CHANGED
@@ -12,14 +12,9 @@ DEFAULT_MAX_NEW_TOKENS = 1024
12
  MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
13
 
14
  DESCRIPTION = """\
15
- # Llama-2 13B Chat
16
 
17
- This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
18
-
19
- 🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
20
-
21
- 🔨 Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
22
- 🐇 For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
23
 
24
  """
25
 
@@ -32,7 +27,7 @@ this demo is governed by the original [license](https://huggingface.co/spaces/hu
32
  """
33
 
34
  if not torch.cuda.is_available():
35
- DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
36
 
37
 
38
  if torch.cuda.is_available():
@@ -139,7 +134,6 @@ chat_interface = gr.ChatInterface(
139
 
140
  with gr.Blocks(css="style.css") as demo:
141
  gr.Markdown(DESCRIPTION)
142
- gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
143
  chat_interface.render()
144
  gr.Markdown(LICENSE)
145
 
 
12
  MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
13
 
14
  DESCRIPTION = """\
15
+ # Labradorite-13b Chat
16
 
17
+ This Space demonstrates model [Labradorite-13b](https://huggingface.co/ibm/labradorite-13b) by IBM, a finetuned Llama 2 model with 13B parameters for chat instructions.
 
 
 
 
 
18
 
19
  """
20
 
 
27
  """
28
 
29
  if not torch.cuda.is_available():
30
+ DESCRIPTION += "\n<p>Running on CPU! This demo does not work on CPU.</p>"
31
 
32
 
33
  if torch.cuda.is_available():
 
134
 
135
  with gr.Blocks(css="style.css") as demo:
136
  gr.Markdown(DESCRIPTION)
 
137
  chat_interface.render()
138
  gr.Markdown(LICENSE)
139