nanogptrs
1.0.0
这是Andrej Karpathy的YT视频的Nanogpt模型的生锈实现:https://www.youtube.com/watch?v=kcc8fmeb1ny&t=12S
在以下帮助的情况下:https://github.com/laurentmazare/tch-rob/blob/main/examples/min-gpt/main.rs and https://github.com/karpathy/karpathy/nanogpty/nanogpt/nanogpt/blob/blob/blob/master/master/model.py.py。
创建Micromamba环境(或CONDA):
micromamba env create -f environment.yml激活环境:
micromamba activate nanogptrs export LD_LIBRARY_PATH=/opt/conda/lib/python3.10/site-packages/torch/lib/: $LD_LIBRARY_PATH./data/download.sh
./models/download.sh gpt2
cargo run --release -- --device=cuda --restore-from models/gpt2/model.safetensors generate --max-len 32 --prompt " Once upon a time " gpt2cargo run --release -- --device=cuda train --n-epochs=3 --final-checkpoint-path=models/nanogptrs.safetensors nano-gpt最终应该(我的泰坦XP上的5h)产生这样的东西:
DUCHESS OF YORK:
Here comes already.
EXTOLY:
O, by the means of your crown?
KING HENRY VI:
Brother, that my lord, change thou givest queen.
KING RICHARD II:
Mine honour, because I am advertised
The queen our is not your voice. Would thy sight
Next Rome, among, insible express to dictliffe:
For ere for goings
Abova drunking redel her food pain soul to every it.
QUEEN MARGARET:
I took! O, if you so, good and the Montague of slave,
That he's breathing which holy a holy brats.