deepgeek/MiniCPM-o
2
0
Fork 0
mirror of https://github.com/OpenBMB/MiniCPM-V.git synced 2026-02-05 18:29:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

update finetuen for multi images sft (#462)

Browse Source
This commit is contained in:
qianyu chen
2024-08-15 11:24:50 +08:00
committed by GitHub
parent 825abf10e2
commit cd64150b51
7 changed files with 170 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
finetune/finetune_lora.sh
View File

@@ -14,6 +14,9 @@ EVAL_DATA="path/to/test_data"
LLM_TYPE="qwen2"
# if use openbmb/MiniCPM-V-2, please set LLM_TYPE=minicpm
#if use openbmb/MiniCPM-Llama3-V-2_5, please set LLM_TYPE=llama3
MODEL_MAX_Length=2048 # if conduct multi-images sft, please set MODEL_MAX_Length=4096
DISTRIBUTED_ARGS="
--nproc_per_node $GPUS_PER_NODE \
--nnodes $NNODES \
@@ -39,7 +42,7 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
--tune_llm false \
--use_lora true \
--lora_target_modules "llm\..*layers\.\d+\.self_attn\.(q_proj|k_proj|v_proj|o_proj)" \
--model_max_length 2048 \
--model_max_length $MODEL_MAX_Length \
--max_slice_nums 9 \
--max_steps 10000 \
--eval_steps 1000 \