Update README.md
Browse files
README.md
CHANGED
@@ -14,8 +14,14 @@ pipeline_tag: conversational
|
|
14 |
---
|
15 |
# Jais-13b-chat-adn
|
16 |
This is a copy of `inception-mbzuai/jais-13b-chat` with handler.py file for an easy deployment on huggingface inference endpoints.
|
17 |
-
|
18 |
-
Please note that the model requires a beefy machine
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
# Jais-13b-chat
|
21 |
|
|
|
14 |
---
|
15 |
# Jais-13b-chat-adn
|
16 |
This is a copy of `inception-mbzuai/jais-13b-chat` with handler.py file for an easy deployment on huggingface inference endpoints.
|
17 |
+
There is now a button `Deploy` in the top right corner (you will need a paid subscription).
|
18 |
+
Please note that the model requires a beefy machine, i.e. GPU [large] · 4x Nvidia Tesla T4 which is $ 4.50 per h, small and medium size machines were not able to start it up.
|
19 |
+
|
20 |
+
Once deployed use sample curl to test (or python code provided at your endpoitnt page)
|
21 |
+
`curl https://YOUR_ENDPOINT.aws.endpoints.huggingface.cloud -X POST -d '{"inputs": "ما هي عاصمة الامارات؟"}' -H "Authorization: Bearer YOUR_TOKEN" -H "Content-Type: application/json"`
|
22 |
+
|
23 |
+
Don't forget to put your endpoint on pause, when idle, to save some cash.
|
24 |
+
|
25 |
|
26 |
# Jais-13b-chat
|
27 |
|