Unofficial python bindings for llama-rs. 🐍❤️🦀
Project description
llama-rs-python
Unofficial python bindings for llama-rs created with PyO3. 🐍❤️🦀
This package gives access to the basic functionality of the llama-rs project.
GGML converted models can be loaded and executed.
Installation
Simply install it via pip: pip install llama-rs-python
Usage
The package is typehinted for easy usage.
A usage example could look like this:
from llama_rs_python import Model
#load the model
model = Model("path/to/model.bin")
#generate
print(model.generate("The meaning of life is"))
The package also supports callbacks to get each token as it is generated.
The callback-function also supports canceling the generation by returning a True
value from the pytohn side.
from llama_rs_python import Model
import sys
from typing import Optional
#load the model
model = Model("path/to/model.bin")
#define the callback
def callback(token:str)->Optional[bool]:
print(token,end="")
sys.stdout.flush()
# (return True here to cancel the generation)
#start generation
model.generate("The meaning of life is",callback=callback)
The configuration of the generation is handled by the GenerationConfig
class.
from llama_rs_python import Model, GenerationConfig
#load the model
model = Model("path/to/model.bin")
#create a config
config = GenerationConfig(top_p=0.9,seed=1441,max_new_tokens=1024)
#generate
print(model.generate("The meaning of life is",generation_config=config))
To configure model specific settings the SessionConfig
class can be used.
from llama_rs_python import Model, SessionConfig
#define the session
session_config = SessionConfig(threads=8,context_length=512)
#load the model
model = Model("path/to/model.bin",session_config=session_config)
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
Built Distributions
Hashes for llama_rs_python-0.0.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0b7f7867fd3972dad85e73de3e05e6ef19f216f50a76ab952ad63b97fe33f31d |
|
MD5 | be960cde9b61785f59f990281371e5ca |
|
BLAKE2b-256 | 86451c485fbc57e1a52a1412c4e1b5c00bb3a4cafc9449f90942e44890099d80 |
Hashes for llama_rs_python-0.0.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | cf819b3124051081744eb4847fc92f9b48c35b47cc947493eb252cd0cf2df586 |
|
MD5 | 9816952c8845268a8aed2e17b58c2eef |
|
BLAKE2b-256 | 707d831ef5d4ae085cea88e24b2f0c54745d75493b0b6f1fedc5af9e6c60d040 |
Hashes for llama_rs_python-0.0.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e4121834e0b5ab8572dabf5fc1dcb07a200f2331fac497ca918de6abc177b15c |
|
MD5 | 00966045f35f387b68ab2bf498ee0b39 |
|
BLAKE2b-256 | 6f635decc5a9e0264205688c284e761ff4531d0a308083aa012efe828cab0d23 |
Hashes for llama_rs_python-0.0.2-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ba893892d106ccb068479b72756b3d2b0d34eb41f5cc7d596cae78efcbca2a71 |
|
MD5 | 10518b2542e3a9154deb7eb771382cb6 |
|
BLAKE2b-256 | 64c415c2639c8070b0f12d1f6757148760cdef80f092299ba3166dec9fb77b42 |
Hashes for llama_rs_python-0.0.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c94dabc00b958429517788539dbf34839ff8f427650b3c79e39b1808153281ee |
|
MD5 | b8d47d297b5d0827cc682463d80970d4 |
|
BLAKE2b-256 | 682f02d64a5f9591d118c59ec8e435aad34e3477f1a7605f216e51d490427cde |
Hashes for llama_rs_python-0.0.2-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f409e07c01bc0f825b533759ef0eb7c351e7f30de9c73c99d132f206a161f399 |
|
MD5 | 767028ea8fea4d8cc5ed8b7e0188f86f |
|
BLAKE2b-256 | 1d8fb81be56b5b2815bebc7859b05130d3da4c1bc9c257c0bac76a2660b8e9fa |
Hashes for llama_rs_python-0.0.2-cp311-none-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e92dbcef8b293a48b7895b0e44b62fe3cdd88fa709c1b8f812fc26d872debe52 |
|
MD5 | 1d8ec67e62c503a237502884f04a82f3 |
|
BLAKE2b-256 | 8feb6043a39dca6030ff430f19325e4930a7bb794cf1032c4227056f45d954ba |
Hashes for llama_rs_python-0.0.2-cp311-none-win32.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 90c5803e705c02b579ad1e4e1737e8d4034ef908b362c17fe2cca0394abfdbf8 |
|
MD5 | 03f5a78fa4d804f31f20f4949a17b86f |
|
BLAKE2b-256 | ae606bab1b32a68c748ae81ce3c4e2319de02e9e6ccd31b0e60642a9214a2db5 |
Hashes for llama_rs_python-0.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 60a9cea2591f8babb96174243e3827505842bc9cfdcbc72d0abd9a79e0cb62de |
|
MD5 | 9116834c8138d9053e965185d81a9662 |
|
BLAKE2b-256 | 199cac04eec3082c7c5201f43d020a247234f95a2cff814ce4109e709f8e7b39 |
Hashes for llama_rs_python-0.0.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 128322681699272c8ec0ff2c95d535d17a459b19aaaddbafc39b33eaf52e8ccf |
|
MD5 | 171f46b2d1d275f8d79b72f5164ee73c |
|
BLAKE2b-256 | 874f30898cb67c89bb1c286662e00f3571148b8d5db121667306d81acf61fae7 |
Hashes for llama_rs_python-0.0.2-cp311-cp311-macosx_11_0_arm64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 313e9ec96766e2bc8a9a479729544218533690ccbf8eab2b413cc67c562b8fb4 |
|
MD5 | b568095d1b5d67c3d28772f3cf08d84b |
|
BLAKE2b-256 | ffc32447c6a760bde01d1b430d5854fe31ae86719c6687e49659626bc7c1de57 |
Hashes for llama_rs_python-0.0.2-cp311-cp311-macosx_10_7_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0bdefab4dbba2b00e174b568b671c1b208225c2384038cb7def6c017978b801d |
|
MD5 | b336208bd851430ca597e6720124fc2f |
|
BLAKE2b-256 | 80d4469d7af8dd7301af9984df0311628b9cee90a523fd5afe7ac649e5f33d07 |
Hashes for llama_rs_python-0.0.2-cp310-none-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a9207f57fe7a6bb9e23d3d70f75ff671867e2c101494412954b5b40fa4d3723a |
|
MD5 | 5b5dd52c93609dd0a80cc2ea8037d4c9 |
|
BLAKE2b-256 | 8b423d370d979416f6d96f3269e47c05f0ae9842b3ab720b92669eff202ffe56 |
Hashes for llama_rs_python-0.0.2-cp310-none-win32.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 50bb4ee58b2dc938a34f45e4e69dd1c753fc624f9532d7c0e270c00b6dce604d |
|
MD5 | 3ebd07b9cb33dd29e9b7190756b1f718 |
|
BLAKE2b-256 | 35e21a97e168b3312ddf250fafece3465ba301f8e1b31de6995ac3a2f89136cf |
Hashes for llama_rs_python-0.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 917dc5131e620d04db562a686e4969f4306d023973e11ab1a9066ddfb7623b35 |
|
MD5 | da47fe048d20c8ec03d9ed4c96a4993e |
|
BLAKE2b-256 | dc32826c0cfc2d1547feb2a9d5307b22511b17c52e8fdabe851ebd6d7207a574 |
Hashes for llama_rs_python-0.0.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | de8658baa39f8ff3065030ad83d2ac2fc595b317ae85cb0240c03539bc91b2c7 |
|
MD5 | 98a6bf07759716f1bff7a9e1f399bd51 |
|
BLAKE2b-256 | 78363d37e04d6f439249e92a8ffbc579c76316d39778a0ab3dcdfdcf12163871 |
Hashes for llama_rs_python-0.0.2-cp310-cp310-macosx_11_0_arm64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 335db0818ce6ce9c2beb21d3813f95f7c204c74f78e516b6fb28dbd746fa5f57 |
|
MD5 | c5f197a2a8f7a9dec394017f01398641 |
|
BLAKE2b-256 | a509cf02e577286f402ad445d14c079384230842c0222d22a7e225f9b948db23 |
Hashes for llama_rs_python-0.0.2-cp310-cp310-macosx_10_7_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2e0baf2aee0e0d237bf6118cc5af125a791f74e50c3e54ade3a2f11af1c53ee1 |
|
MD5 | 88efa2f4a4509edbd841c55cc5686b71 |
|
BLAKE2b-256 | 9a1eb33f82f44266afa5f54322c4d8b2cc40c296914e4497efa133dbc05aed51 |
Hashes for llama_rs_python-0.0.2-cp39-none-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5056b61a8edf79af0443dc16451fcb10b93c27cc164168120feb14c6cd49f2ec |
|
MD5 | 5120e918b1930ad8cd4ec06be835099d |
|
BLAKE2b-256 | 3686445a05d13ccaac4da5b2d217cd4c86b42201cdbd78878317b3942800e064 |
Hashes for llama_rs_python-0.0.2-cp39-none-win32.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9e818911b90b343a966c0f316307878432601dcfd8c7abfe95e71ba0bba6bd97 |
|
MD5 | c15e83a5bd99e865c1a98a406495a9f5 |
|
BLAKE2b-256 | ad89d399d900b4e80609e0271c4f592bfa5df86b5e436d1b4c6edda2a8831295 |
Hashes for llama_rs_python-0.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7fb29e971139dc0ff140e6783629bc4897ca5edf00acd7ccc9f464fba799e090 |
|
MD5 | c26d9da7c86bc29ae9e1afc559add0f6 |
|
BLAKE2b-256 | ae9315c48052f15b91b41f635fb85a7510ff31eca129589c7476070f8c22e18e |
Hashes for llama_rs_python-0.0.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 660aba80e6a9f0edc4f43498438abc3a988c8458c3626f7df32a7a7ecc2d1700 |
|
MD5 | f82ac66e7a36ffb740f30d41726e0c67 |
|
BLAKE2b-256 | 41dd516af383f2d5314fb4ba273703093df08937590c0c4b7f6dd1b80dfe0aa8 |
Hashes for llama_rs_python-0.0.2-cp38-none-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3ae164b1aa07ad94e1f433da3f9b650e34b5f33fa635e082773ed17bbf8fc0b2 |
|
MD5 | ef5f19506b0bb8ac5bd6a424ab07d8b0 |
|
BLAKE2b-256 | 188521c3e3fc76d7a12a01b7d11c18da073373dbcfdf44d5ee09af4d275f3256 |
Hashes for llama_rs_python-0.0.2-cp38-none-win32.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 73267b4429a4e1ec9c1645ac70cf781c023418cbb96cbd68c2350e485e3602ca |
|
MD5 | 872a3693c97ac8c0698b8f6f597a856c |
|
BLAKE2b-256 | 1ac370bbd7bb350c5138d6c5fdd73c26caecd17b68de007f2a19271534ab41ac |
Hashes for llama_rs_python-0.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 876629a4e3528954e4dc37ef3e0c4607c131c6f78aeabf351e46c8123f87c88e |
|
MD5 | 9f778307f3b8d2348ff140b07bbfb465 |
|
BLAKE2b-256 | ddbaf8b2a742a76c696ea22aaaea55719cecac69a7db2726b410b220fc69429a |
Hashes for llama_rs_python-0.0.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 31433f0739882205e54be4f409e75d23292e91532f4cb681ef27cf38b7e9d2da |
|
MD5 | 306415aba6c988917681b982a9966928 |
|
BLAKE2b-256 | d7f6bffb18218ae596d4b53576b1bb1b2432a15488e51da6ae24ca2935523988 |
Hashes for llama_rs_python-0.0.2-cp37-none-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f76ba08a1f26ec80693f8587a3137256e6aa53f55e780d14cf7d9be0b3a7f392 |
|
MD5 | 00391e9359ab1297c8c444c785a761da |
|
BLAKE2b-256 | 6ef7e0cb7d34fa890cc0ac39e138f3bd2b9b7a7b2c7a858769fd023c33339427 |
Hashes for llama_rs_python-0.0.2-cp37-none-win32.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ad8de6dba4cdcaef5af3cbc9f4cfcd6558ec533617d43985b443818a1b67f48e |
|
MD5 | a7233c1e57cde2fa248d8116813a4eb2 |
|
BLAKE2b-256 | 515593372cfe8d5fdfcb18d4c02bc0ee907a0e8696c8d672bd5210c2b1ab8963 |
Hashes for llama_rs_python-0.0.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e7844ce51d73bd1eec58875bf306b5726c77cea3d66bc359fc618893db7b1ce1 |
|
MD5 | f6830e250d12deb62bf5362afcf5fa8f |
|
BLAKE2b-256 | da5bc62ddb14856519b4a93520f5e724405bd827a47b78f686ff8804e5e732bf |
Hashes for llama_rs_python-0.0.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 46d62b4a224626d8cc499826bd87f3a8713ef9aa412c060770c68da0a8793c8d |
|
MD5 | a7cd71486c6a76e856eefa565c3df09a |
|
BLAKE2b-256 | 0db736299e0ba41b7f9a64d363c1ded3e1a86ee024473454b1c81084ca022f63 |