Halaman utama Jelajahi Bantuan
Masuk
cturan
/
llama.cpp
cermin dari https://github.com/cturan/llama.cpp
1
0
Fork 0
Berkas Masalah 0 Wiki
Pohon: 741ca7dd1c
Ranting Tag
llama.cpp
/
examples
/
train-text-from-scratch
Georgi Gerganov ef3f333d37 ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709) 2 tahun lalu
..
CMakeLists.txt b1f4290953 cmake : install targets (#2256) 2 tahun lalu
README.md 92f20d9942 train : get raw text instead of page with html (#1905) 2 tahun lalu
train-text-from-scratch.cpp ef3f333d37 ggml : sync latest (SAM + SD operators, CUDA alibi) (#2709) 2 tahun lalu

README.md

train-text-from-scratch

Basic usage instructions:

# get training data
wget https://raw.githubusercontent.com/brunoklein99/deep-learning-notes/master/shakespeare.txt

# train
./bin/train-text-from-scratch \
        --vocab-model ../models/ggml-vocab.bin \
        --ctx 64 --embd 256 --head 8 --layer 16 \
        --checkpoint-in  chk-shakespeare-256x16.bin \
        --checkpoint-out chk-shakespeare-256x16.bin \
        --model-out ggml-shakespeare-256x16-f32.bin \
        --train-data "shakespeare.txt" \
        -t 6 -b 16 -n 32 --seed 1 --adam-iter 16 \
        --print-details-interval 0 --predict 16 --use-flash

# predict
./bin/main -m ggml-shakespeare-256x16-f32.bin