History

Steve Grubb 6e0438da3c gguf : fix resource leaks (#6061 ) There several places where a gguf context is allocated. A call to gguf_free is missing in some error paths. Also on linux, llama-bench was missing a fclose.		2024-03-14 20:29:32 +02:00
..
CMakeLists.txt	cmake : install targets (#2256 )	2023-07-19 10:01:11 +03:00
convert-train-checkpoint-to-gguf.py	gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981 )	2023-11-11 08:04:50 +03:00
README.md	train : finetune LORA (#2632 )	2023-09-28 21:40:11 +03:00
train-text-from-scratch.cpp	gguf : fix resource leaks (#6061 )	2024-03-14 20:29:32 +02:00

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-llama.gguf \
        --ctx 64 --embd 256 --head 8 --layer 16 \
        --checkpoint-in  chk-shakespeare-256x16-LATEST.gguf \
        --checkpoint-out chk-shakespeare-256x16-ITERATION.gguf \
        --model-out ggml-shakespeare-256x16-f32-ITERATION.gguf \
        --train-data "shakespeare.txt" \
        -t 6 -b 16 --seed 1 --adam-iter 256 \
        --no-checkpointing

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

Output files will be saved every N iterations (config with --save-every N). The pattern "ITERATION" in the output filenames will be replaced with the iteration number and "LATEST" for the latest output.

To train GGUF models just pass them to --checkpoint-in FN.