Skip to main content

fleece-worker

Project description

Installation

Install From PyPI

pip install fleece-worker

Install From Source

pip install -e .

Connect to a controller

python -m fleece-worker -c <controller_url>  -t <api_token>

Optional: --worker-nickname abc, --heartbeat-interval 10, -w <worker_url>

For example:

python -m fleece-worker -c https://serving-api.colearn.cloud:8443 -t <api_token>

Try it out (deprecated)

python -m fleece-worker
curl localhost:8080/forward -H 'Content-Type: application/json' -d '{"task_id":"123","step":0,"round":0,"plan":[["http://127.0.0.1:8080",["llama-2-7b-chat-slice/tok_embeddings", "llama-2-7b-chat-slice/layers.0", "llama-2-7b-chat-slice/layers.1", "llama-2-7b-chat-slice/layers.2", "llama-2-7b-chat-slice/layers.3", "llama-2-7b-chat-slice/layers.4", "llama-2-7b-chat-slice/layers.5", "llama-2-7b-chat-slice/layers.6", "llama-2-7b-chat-slice/layers.7", "llama-2-7b-chat-slice/layers.8", "llama-2-7b-chat-slice/layers.9", "llama-2-7b-chat-slice/layers.10", "llama-2-7b-chat-slice/layers.11", "llama-2-7b-chat-slice/layers.12", "llama-2-7b-chat-slice/layers.13", "llama-2-7b-chat-slice/layers.14", "llama-2-7b-chat-slice/layers.15", "llama-2-7b-chat-slice/layers.16", "llama-2-7b-chat-slice/layers.17", "llama-2-7b-chat-slice/layers.18", "llama-2-7b-chat-slice/layers.19", "llama-2-7b-chat-slice/layers.20", "llama-2-7b-chat-slice/layers.21", "llama-2-7b-chat-slice/layers.22", "llama-2-7b-chat-slice/layers.23", "llama-2-7b-chat-slice/layers.24", "llama-2-7b-chat-slice/layers.25", "llama-2-7b-chat-slice/layers.26", "llama-2-7b-chat-slice/layers.27", "llama-2-7b-chat-slice/layers.28", "llama-2-7b-chat-slice/layers.29", "llama-2-7b-chat-slice/layers.30", "llama-2-7b-chat-slice/layers.31", "llama-2-7b-chat-slice/norm", "llama-2-7b-chat-slice/output"]]],"payload":[[1, 518, 25580, 29962, 825, 338, 278,  9522, 412, 310, 1122, 11586, 895, 29973, 518, 29914, 25580, 29962]]}'
curl localhost:8080/forward -H 'Content-Type: application/json' -d '{"task_id":"123","step":0,"round":0,"plan":[["http://127.0.0.1:8080",["llama-2-7b-chat-slice/tok_embeddings", "llama-2-7b-chat-slice/layers.0", "llama-2-7b-chat-slice/layers.1", "llama-2-7b-chat-slice/layers.2", "llama-2-7b-chat-slice/layers.3", "llama-2-7b-chat-slice/layers.4", "llama-2-7b-chat-slice/layers.5", "llama-2-7b-chat-slice/layers.6", "llama-2-7b-chat-slice/layers.7", "llama-2-7b-chat-slice/layers.8", "llama-2-7b-chat-slice/layers.9", "llama-2-7b-chat-slice/layers.10", "llama-2-7b-chat-slice/layers.11", "llama-2-7b-chat-slice/layers.12", "llama-2-7b-chat-slice/layers.13", "llama-2-7b-chat-slice/layers.14", "llama-2-7b-chat-slice/layers.15", "llama-2-7b-chat-slice/layers.16", "llama-2-7b-chat-slice/layers.17", "llama-2-7b-chat-slice/layers.18", "llama-2-7b-chat-slice/layers.19", "llama-2-7b-chat-slice/layers.20", "llama-2-7b-chat-slice/layers.21", "llama-2-7b-chat-slice/layers.22", "llama-2-7b-chat-slice/layers.23", "llama-2-7b-chat-slice/layers.24", "llama-2-7b-chat-slice/layers.25", "llama-2-7b-chat-slice/layers.26", "llama-2-7b-chat-slice/layers.27", "llama-2-7b-chat-slice/layers.28", "llama-2-7b-chat-slice/layers.29", "llama-2-7b-chat-slice/layers.30", "llama-2-7b-chat-slice/layers.31", "llama-2-7b-chat-slice/norm", "llama-2-7b-chat-slice/output"]]],"payload":[[1, 518, 25580, 29962, 825, 338, 278, 9522, 412, 310, 1122, 11586, 895, 29973, 518, 29914, 25580, 29962], [1, 518, 25580, 29962, 3532, 14816, 29903, 6778, 13, 2499, 1994, 1234, 411, 5952, 18282, 13, 29966, 829, 14816, 29903, 6778, 13, 13, 29902, 626, 2675, 304, 3681, 29892, 825, 881, 306, 1074, 29973, 518, 29914, 25580, 29962], [1, 518, 25580, 29962, 3532, 14816, 29903, 6778, 13, 2499, 1994, 1234, 411, 953, 3848, 275, 13, 29966, 829, 14816, 29903, 6778, 13, 13, 5328, 304, 748, 515, 1522, 823, 292, 304, 23526, 29973, 518, 29914, 25580, 29962]]}'

note that the model will be automatically downloaded to ~/.cache

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fleece-worker-0.1.0.tar.gz (16.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fleece_worker-0.1.0-py3-none-any.whl (16.5 kB view details)

Uploaded Python 3

File details

Details for the file fleece-worker-0.1.0.tar.gz.

File metadata

  • Download URL: fleece-worker-0.1.0.tar.gz
  • Upload date:
  • Size: 16.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.0.0 CPython/3.12.2

File hashes

Hashes for fleece-worker-0.1.0.tar.gz
Algorithm Hash digest
SHA256 1836e21952d27c8dbd11334e3d18a9d4c22348ba1f57b69d60756f2f4b87415d
MD5 367fcad24266511a4be63d31854566b9
BLAKE2b-256 7de0711b89d81400c776f6ca85894ecc31b8fe43a1317a8877bf70e76d83a4f6

See more details on using hashes here.

File details

Details for the file fleece_worker-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: fleece_worker-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 16.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.0.0 CPython/3.12.2

File hashes

Hashes for fleece_worker-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8168384ef7242f78541fd916f3f09c9ffd3767523d1dc9262fb834e32503ce07
MD5 62f1e11f3b971edf152874de5e849f84
BLAKE2b-256 eddae1f744374fe14c693a625bf198ceb3dbeb169776ec417b770a42852cab31

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page