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 to MiniCPM-o 2.6

Browse Source
This commit is contained in:
yiranyyu
2025-01-14 15:33:44 +08:00
parent b75a362dd6
commit 53c0174797
123 changed files with 16848 additions and 2952 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
finetune/finetune_ds.sh
View File

@@ -5,14 +5,17 @@ NNODES=1
NODE_RANK=0
MASTER_ADDR=localhost
MASTER_PORT=6001
MODEL="openbmb/MiniCPM-V-2_6"
# or openbmb/MiniCPM-V-2, openbmb/MiniCPM-Llama3-V-2_5
MODEL="openbmb/MiniCPM-o-2_6"
# or openbmb/MiniCPM-V-2, openbmb/MiniCPM-Llama3-V-2_5, openbmb/MiniCPM-V-2_6
# ATTENTION: specify the path to your training data, which should be a json file consisting of a list of conversations.
# See the section for finetuning in README for more information.
DATA="path/to/trainging_data"
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"
# if use openbmb/MiniCPM-V-2, please set LLM_TYPE=minicpm, if use openbmb/MiniCPM-Llama3-V-2_5, please set LLM_TYPE="llama3",
# if use openbmb/MiniCPM-o-2_6 or openbmb/MiniCPM-V-2_6, please set LLM_TYPE=qwen
LLM_TYPE="qwen"
MODEL_MAX_Length=2048 # if conduct multi-images sft, please set MODEL_MAX_Length=4096
@@ -38,7 +41,7 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
--do_train \
--do_eval \
--tune_vision true \
--tune_llm true \
--tune_llm false \
--model_max_length $MODEL_MAX_Length \
--max_slice_nums 9 \
--max_steps 10000 \
@@ -60,5 +63,5 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--gradient_checkpointing true \
--deepspeed ds_config_zero2.json \
--deepspeed ds_config_zero3.json \
--report_to "tensorboard"