A Python Wrapper for Dalai
Project description
dalaipy
A Python Wrapper for Dalai!
Dalai is a simple, and easy way to run LLaMa and Alpaca locally.
Installation
pip install dalaipy
Instructions
- Go to Dalai, and set up your model of choice on your system (either Mac, Windows, or Linux). The readme provides clear explanations!
- Once you can run
npx dalai serve
, run the server and test out your model of choice. - Install dalaipy per the instructions above, and make your first request:
from dalaipy.src import Dalai
model = Dalai()
# your_model can be one of the following, "alpaca.7B", "alpaca.13B", "llama.7B", "llama.13B", "llama.30B", or "llama.65B", and is dictated by which model you installed
request = model.generate_request("What is the capital of the United States?", your_model)
print(model.generate(request))
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
dalaipy-2.0.1.tar.gz
(3.5 kB
view details)
Built Distribution
File details
Details for the file dalaipy-2.0.1.tar.gz
.
File metadata
- Download URL: dalaipy-2.0.1.tar.gz
- Upload date:
- Size: 3.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 738822ef0310c01f60f3f903dc20532b38c77f0faf991a73d0a4c740f788bb13 |
|
MD5 | ca2acbd144039b99ae930de3b7cbb30e |
|
BLAKE2b-256 | 81bf3020e9c98fb52724119699c9db9ff9677fe51df4491fe2252e024e227fa8 |
File details
Details for the file dalaipy-2.0.1-py3-none-any.whl
.
File metadata
- Download URL: dalaipy-2.0.1-py3-none-any.whl
- Upload date:
- Size: 4.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1289475726a04caf470560b0149cd568aa14672e8e67e44216ae4a8dac53c02b |
|
MD5 | 5c99ecb1597fc45b6b5c06c5895c9400 |
|
BLAKE2b-256 | df9ecd05b3dc879369998a1005026021c11fe33f5240d08606cd0f01e013c008 |