A collection of tricks to speed up LLMs, see our transformer-tricks papers on arXiv
Project description
Setup
pip3 install --quiet -r requirements.txt
To run llama and other LLMs that need an agreement (not SmolLM), you first have to type the following:
huggingface-cli login
Above will ask you for the hf_token, which is the same you use e.g. in colab
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 Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file transformer_tricks-0.1.3.tar.gz.
File metadata
- Download URL: transformer_tricks-0.1.3.tar.gz
- Upload date:
- Size: 3.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6a0d0216047cffe53d1e587e57679b094e5a96adf395d7c512d9593534caf6df
|
|
| MD5 |
57db546261c1b0d2f12396251cda822d
|
|
| BLAKE2b-256 |
a0185d1bdf2acdd13f9718fbbf06921efd922564f9f44757779b2baff270a047
|
File details
Details for the file transformer_tricks-0.1.3-py3-none-any.whl.
File metadata
- Download URL: transformer_tricks-0.1.3-py3-none-any.whl
- Upload date:
- Size: 4.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d436623f4996ca140225b22c0d5c0f9cefa03fc2df47ad12ef08d0aac6489b64
|
|
| MD5 |
938a06346583c926bac7db10d3c9a9a0
|
|
| BLAKE2b-256 |
fe83c3dc5b8efc5d688fd4821edf07f915947459bb7e46d03f85db86c6fe3825
|
