mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-03 09:22:01 +00:00
92f20d9942
We probably want to train using just the text of Shakespeare instead of the html of the page displaying his work.
23 lines
692 B
Markdown
23 lines
692 B
Markdown
# train-text-from-scratch
|
|
|
|
Basic usage instructions:
|
|
|
|
```bash
|
|
# 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
|
|
```
|