vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

微调脚本优化

Browse source
This commit is contained in:
supermy 2023-11-24 14:18:01 +08:00
parent 2c97ce073e
commit c2ad2b02f3
2 changed files with 12 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

10
examples/finetune/README.md
View file

@ -28,38 +28,38 @@ wget https://raw.githubusercontent.com/brunoklein99/deep-learning-notes/master/s
# ./bin/main -m open-llama-3b-v2-q8_0.gguf --lora lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.bin
# mac os mistral
dataset=slqm \
data_dir="../models/" \
model_dir="../models/ggmls/" \
model_name="openbuddy-mistral-7b-v13.1-q2_k" \
dataset=slqm \
sh examples/finetune/finetune.sh >${model_name}.log
#云电脑 mistral
dataset=slqm \
data_dir="../" \
model_dir="../" \
dataset=slqm \
model_name="openbuddy-mistral-7b-v13.1-q2_k" \
sh examples/finetune/finetune.sh >${model_name}.log
# mac os llama2
dataset=slqm \
data_dir="../models/" \
model_dir="../models/ggmls/" \
model_name="chinese-llama-2-7b-16k.Q2_K" \
dataset=slqm \
sh examples/finetune/finetune.sh >${model_name}.log
#云电脑 llama2
dataset="slqm" \
data_dir="../" \
model_dir="../" \
dataset=slqm \
model_name="chinese-llama-2-7b-16k.Q2_K" \
sh examples/finetune/finetune.sh >${model_name}.log
#云电脑 finetune-bc
dataset="slqm" \
data_dir="../" \
model_dir="../" \
dataset=slqm \
model_name="bc2-7b-chat-q2_k" \
cmd="finetune-bc" \
sh examples/finetune/finetune.sh >${model_name}.log

14
examples/finetune/finetune.sh
View file

@ -12,22 +12,22 @@ fi
./${finetune} \
--train-data ${data_dir}/${dataset}.txt \
--model-base ${model_dir}/${model_name}.gguf \
--checkpoint-in ${model_dir}/chk/chk-${model_name}-LATEST.gguf \
--checkpoint-out ${model_dir}/chk/chk-${model_name}-ITERATION.gguf \
--lora-out ${model_dir}/lora/lora-${model_name}-ITERATION.bin \
--checkpoint-in ${model_dir}/chk/chk-${dataset}-${model_name}-LATEST.gguf \
--checkpoint-out ${model_dir}/chk/chk-${dataset}-${model_name}-ITERATION.gguf \
--lora-out ${model_dir}/lora/lora-${dataset}-${model_name}-ITERATION.bin \
--threads 4 --ctx 64 --batch 4 --adam-iter 1 --save-every 5 \
--lora-r 8 --lora-alpha 16 \
--grad-acc 1 \
--escape \
--epochs 3 \
--use-checkpointing
# # --grad-acc 1 \
# # --use-flash \
# # --escape \
# # --seed 1
./export-lora \
--model-base ${model_dir}/${model_name}.gguf \
--model-out ${model_dir}/${dataset}-${model_name}.gguf \
--lora-scaled ${model_dir}/lora/lora-${model_name}-LATEST.bin 1.0
--lora-scaled ${model_dir}/lora/lora-${dataset}-${model_name}-LATEST.bin 1.0
./main \
-m ${model_dir}/${dataset}-${model_name}.gguf \