TogetherAI
commited on
Commit
•
4e660cb
1
Parent(s):
8439d1b
Update app.py
Browse files
app.py
CHANGED
@@ -1,9 +1,6 @@
|
|
1 |
import gradio as gr
|
2 |
from gradio_client import Client
|
3 |
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
title = "Llama2 70B Chatbot"
|
8 |
description = """
|
9 |
This Space demonstrates model [Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) by Meta, a Llama 2 model with 70B parameters fine-tuned for chat instructions.
|
@@ -12,7 +9,6 @@ This Space demonstrates model [Llama-2-70b-chat-hf](https://huggingface.co/meta-
|
|
12 |
| 7B | [Link](https://huggingface.co/meta-llama/Llama-2-7b) | [Link](https://huggingface.co/meta-llama/Llama-2-7b-hf) | [Link](https://huggingface.co/meta-llama/Llama-2-7b-chat) | [Link](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) |
|
13 |
| 13B | [Link](https://huggingface.co/meta-llama/Llama-2-13b) | [Link](https://huggingface.co/meta-llama/Llama-2-13b-hf) | [Link](https://huggingface.co/meta-llama/Llama-2-13b-chat) | [Link](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) |
|
14 |
| 70B | [Link](https://huggingface.co/meta-llama/Llama-2-70b) | [Link](https://huggingface.co/meta-llama/Llama-2-70b-hf) | [Link](https://huggingface.co/meta-llama/Llama-2-70b-chat) | [Link](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) |
|
15 |
-
|
16 |
"""
|
17 |
css = """.toast-wrap { display: none !important } """
|
18 |
examples=[
|
@@ -21,30 +17,25 @@ examples=[
|
|
21 |
['Explain the plot of Cinderella in a sentence.'],
|
22 |
['How many hours does it take a man to eat a Helicopter?'],
|
23 |
["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
|
24 |
-
|
25 |
-
|
26 |
|
27 |
# Stream text
|
28 |
def predict(message, chatbot, system_prompt="", temperature=0.9, max_new_tokens=4096):
|
29 |
|
30 |
client = Client("https://ysharma-explore-llamav2-with-tgi.hf.space/")
|
31 |
return client.predict(
|
32 |
-
|
33 |
-
system_prompt,
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
)
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
|
45 |
# Gradio Demo
|
46 |
-
with gr.Blocks(theme=
|
47 |
gr.DuplicateButton()
|
48 |
gr.ChatInterface(predict, title=title, description=description, css=css, examples=examples)
|
49 |
|
50 |
-
demo.queue().launch(debug=True)
|
|
|
1 |
import gradio as gr
|
2 |
from gradio_client import Client
|
3 |
|
|
|
|
|
|
|
4 |
title = "Llama2 70B Chatbot"
|
5 |
description = """
|
6 |
This Space demonstrates model [Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) by Meta, a Llama 2 model with 70B parameters fine-tuned for chat instructions.
|
|
|
9 |
| 7B | [Link](https://huggingface.co/meta-llama/Llama-2-7b) | [Link](https://huggingface.co/meta-llama/Llama-2-7b-hf) | [Link](https://huggingface.co/meta-llama/Llama-2-7b-chat) | [Link](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) |
|
10 |
| 13B | [Link](https://huggingface.co/meta-llama/Llama-2-13b) | [Link](https://huggingface.co/meta-llama/Llama-2-13b-hf) | [Link](https://huggingface.co/meta-llama/Llama-2-13b-chat) | [Link](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) |
|
11 |
| 70B | [Link](https://huggingface.co/meta-llama/Llama-2-70b) | [Link](https://huggingface.co/meta-llama/Llama-2-70b-hf) | [Link](https://huggingface.co/meta-llama/Llama-2-70b-chat) | [Link](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) |
|
|
|
12 |
"""
|
13 |
css = """.toast-wrap { display: none !important } """
|
14 |
examples=[
|
|
|
17 |
['Explain the plot of Cinderella in a sentence.'],
|
18 |
['How many hours does it take a man to eat a Helicopter?'],
|
19 |
["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
|
20 |
+
]
|
|
|
21 |
|
22 |
# Stream text
|
23 |
def predict(message, chatbot, system_prompt="", temperature=0.9, max_new_tokens=4096):
|
24 |
|
25 |
client = Client("https://ysharma-explore-llamav2-with-tgi.hf.space/")
|
26 |
return client.predict(
|
27 |
+
message, # str in 'Message' Textbox component
|
28 |
+
system_prompt, # str in 'Optional system prompt' Textbox component
|
29 |
+
temperature, # int | float (numeric value between 0.0 and 1.0)
|
30 |
+
max_new_tokens, # int | float (numeric value between 0 and 4096)
|
31 |
+
0.3, # int | float (numeric value between 0.0 and 1)
|
32 |
+
1, # int | float (numeric value between 1.0 and 2.0)
|
33 |
+
api_name="/chat"
|
34 |
)
|
|
|
|
|
|
|
|
|
35 |
|
36 |
# Gradio Demo
|
37 |
+
with gr.Blocks(theme="ParityError/Interstellar") as demo:
|
38 |
gr.DuplicateButton()
|
39 |
gr.ChatInterface(predict, title=title, description=description, css=css, examples=examples)
|
40 |
|
41 |
+
demo.queue().launch(debug=True)
|