Commit
•
da4bdce
1
Parent(s):
888a129
code
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
title: Llama 2 70b Chat Hf
|
3 |
-
emoji:
|
4 |
colorFrom: blue
|
5 |
colorTo: indigo
|
6 |
sdk: gradio
|
|
|
1 |
---
|
2 |
title: Llama 2 70b Chat Hf
|
3 |
+
emoji: 🦙
|
4 |
colorFrom: blue
|
5 |
colorTo: indigo
|
6 |
sdk: gradio
|
app.py
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
|
3 |
+
with gr.Blocks() as demo:
|
4 |
+
gr.Markdown("""
|
5 |
+
# Llama-2-70b-chat-hf Discord Bot Powered by Gradio and Hugging Face Endpoints
|
6 |
+
|
7 |
+
Make sure you read the 'Special Consideration' section below first! 🦙
|
8 |
+
|
9 |
+
### First install the `gradio_client`
|
10 |
+
|
11 |
+
```bash
|
12 |
+
pip install gradio_client
|
13 |
+
```
|
14 |
+
|
15 |
+
### Then deploy to discord in one line! ⚡️
|
16 |
+
|
17 |
+
```python
|
18 |
+
grc.Client("ysharma/Explore_llamav2_with_TGI").deploy_discord(to_id="llama2-70b-discord-bot")
|
19 |
+
```
|
20 |
+
|
21 |
+
""")
|
22 |
+
with gr.Accordion(label="Special Considerations", open=False):
|
23 |
+
gr.Markdown("""
|
24 |
+
This discord bot will use a FREE Inference Endpoint provided by Hugging Face.
|
25 |
+
Hugging Face does not commit to paying for this endpoint in perpetuity so there is no guarantee your bot will always work.
|
26 |
+
If you would like more control over the infrastructure backing the llama 70b model, consider deploying your own inference endpoint.
|
27 |
+
"""
|
28 |
+
)
|
29 |
+
gr.Markdown("""
|
30 |
+
Note: As a derivate work of [Llama-2-70b-chat](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) by Meta, this demo is governed by the original [license](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI/blob/main/USE_POLICY.md)
|
31 |
+
""")
|
32 |
+
|
33 |
+
|
34 |
+
demo.queue(concurrency_count=70).launch()
|