ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Fix DPO finetuning example (#12313)

Browse source
This commit is contained in:
Jin, Qiao 2024-11-01 13:29:44 +08:00 committed by GitHub
parent 05c5d0267a
commit 126f95be80
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
python/llm/example/GPU/LLM-Finetuning/DPO/README.md
View file

@ -17,8 +17,9 @@ conda create -n llm python=3.11
conda activate llm conda activate llm
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default # below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
pip install transformers==4.36.0 datasets pip install datasets
pip install trl peft==0.10.0 pip install peft==0.10.0
pip install 'trl<0.9'
# Note, if you don't want to reinstall BNBs dependencies, append the `--no-deps` flag! # Note, if you don't want to reinstall BNBs dependencies, append the `--no-deps` flag!
pip install --no-deps --force-reinstall 'https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_multi-backend-refactor/bitsandbytes-0.44.1.dev0-py3-none-manylinux_2_24_x86_64.whl' pip install --no-deps --force-reinstall 'https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_multi-backend-refactor/bitsandbytes-0.44.1.dev0-py3-none-manylinux_2_24_x86_64.whl'
``` ```

4
python/llm/example/GPU/LLM-Finetuning/DPO/dpo_finetuning.py
View file

@ -34,12 +34,12 @@
import os import os
import torch import torch
from ipex_llm.transformers.qlora import get_peft_model, prepare_model_for_kbit_training
from ipex_llm.transformers import AutoModelForCausalLM
import transformers import transformers
from transformers import AutoTokenizer, TrainingArguments, BitsAndBytesConfig from transformers import AutoTokenizer, TrainingArguments, BitsAndBytesConfig
from datasets import load_dataset from datasets import load_dataset
from peft import LoraConfig from peft import LoraConfig
from ipex_llm.transformers.qlora import get_peft_model, prepare_model_for_kbit_training
from ipex_llm.transformers import AutoModelForCausalLM
from trl import DPOTrainer from trl import DPOTrainer
import argparse import argparse