Steve Huguenin-Elie
commited on
Commit
·
2805de5
1
Parent(s):
e880564
Customize chat for the multi-domain customer chat bot
Browse files
app.py
CHANGED
@@ -14,19 +14,17 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
|
|
14 |
DESCRIPTION = """\
|
15 |
# Llama-2 7B Chat
|
16 |
|
17 |
-
This Space demonstrates model [
|
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 [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
|
22 |
"""
|
23 |
|
24 |
LICENSE = """
|
25 |
<p/>
|
26 |
|
27 |
---
|
28 |
-
As a derivate work of [
|
29 |
-
this demo is governed by the original [license](https://huggingface.co/spaces/
|
30 |
"""
|
31 |
|
32 |
if not torch.cuda.is_available():
|
@@ -127,11 +125,11 @@ chat_interface = gr.ChatInterface(
|
|
127 |
],
|
128 |
stop_btn=None,
|
129 |
examples=[
|
130 |
-
["
|
131 |
-
["
|
132 |
-
["
|
133 |
-
["
|
134 |
-
["
|
135 |
],
|
136 |
)
|
137 |
|
|
|
14 |
DESCRIPTION = """\
|
15 |
# Llama-2 7B Chat
|
16 |
|
17 |
+
This Space demonstrates model [llama-2-7b-bics-multi_woz_v22](https://huggingface.co/stevugnin/llama-2-7b-bics-multi_woz_v22) by University of Luxembourg FSTM, a Llama 2 model with 7B parameters fine-tuned for multi-domain customer support 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 |
|
22 |
LICENSE = """
|
23 |
<p/>
|
24 |
|
25 |
---
|
26 |
+
As a derivate work of [llama-2-7b-bics-multi_woz_v22](https://huggingface.co/stevugnin/llama-2-7b-bics-multi_woz_v22) by University of Luxembourg FSTM,
|
27 |
+
this demo is governed by the original [license](https://huggingface.co/spaces/stevugnin/multi-domain-customer-support-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/stevugnin/multi-domain-customer-support-chat/blob/main/USE_POLICY.md).
|
28 |
"""
|
29 |
|
30 |
if not torch.cuda.is_available():
|
|
|
125 |
],
|
126 |
stop_btn=None,
|
127 |
examples=[
|
128 |
+
["Hi there! Can you give me some info on Cityroomz?"],
|
129 |
+
["I am looking for a restaurant. I would like something cheap that has Chinese food."],
|
130 |
+
["Please find me a train from Cambridge to Stansted airport."],
|
131 |
+
["I'd like a train from Leicester to Cambridge, please!"],
|
132 |
+
["Hi, I'm traveling to Cambridge soon and am looking forward to seeing some local tourist attractions."],
|
133 |
],
|
134 |
)
|
135 |
|