[Bug] Weights cannot be loaded after fine-tuning lora model

HarryK4673 commented 1 month ago

Checklist

[X] 1. I have searched related issues but cannot get the expected help.
[X] 2. The bug has not been fixed in the latest version.
[X] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

Cannot use AutoModelForCausalLM.from_pretrained to load model. Some parameters cannot be loaded correctly. Cannot use peft to load model, since no adapter_config.json in the folder after fine-tuning.

Reproduction

path = "path/to/fine-tuning/model"
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True,
    device_map='auto').eval()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

question = 'Hello, who are you?'
response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

Or

model = AutoModelForCausalLM.from_pretrained("path_to_base_model")
peft_config = PeftConfig.from_pretrained("path_to_lora_folder")
model = PeftModel.from_pretrained(model, "path_to_lora_folder")

Environment

sys.platform: linux
Python: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3: NVIDIA A10G
CUDA_HOME: /usr
NVCC: Cuda compilation tools, release 10.1, V10.1.24
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
PyTorch: 2.1.2+cu121
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v3.1.1 (Git Hash 64f6bcbcbab628e96f33a62c3e975f8535a7bde4)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 12.1
  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
  - CuDNN 8.9.2
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.9.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-invalid-partial-specialization -Wno-unused-private-field -Wno-aligned-allocation-unavailable -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.1.2, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

TorchVision: 0.16.2+cu121
LMDeploy: 0.5.3+
transformers: 4.40.0
gradio: 4.41.0
fastapi: 0.112.2
pydantic: 2.8.2
triton: 2.1.0
NVIDIA Topology: 
        GPU0    GPU1    GPU2    GPU3    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      PHB     PHB     PHB     0-47    0               N/A
GPU1    PHB      X      PHB     PHB     0-47    0               N/A
GPU2    PHB     PHB      X      PHB     0-47    0               N/A
GPU3    PHB     PHB     PHB      X      0-47    0               N/A

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

Error traceback

Traceback (most recent call last):
  File "/home/ubuntu/Documents/something/0928/internvl2.py", line 188, in <module>
    response, history = model.chat(tokenizer, pixel, question, generation_config, history=None, return_history=True)
  File "/home/ubuntu/.cache/huggingface/modules/transformers_modules/internvl2_4b_phi3_3_8b_dynamic_res_2nd_finetune_lora/modeling_internvl_chat.py", line 290, in chat
    generation_output = self.generate(
  File "/home/ubuntu/anaconda3/envs/env/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/ubuntu/.cache/huggingface/modules/transformers_modules/internvl2_4b_phi3_3_8b_dynamic_res_2nd_finetune_lora/modeling_internvl_chat.py", line 340, in generate
    outputs = self.language_model.generate(
  File "/home/ubuntu/anaconda3/envs/env/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/ubuntu/anaconda3/envs/env/lib/python3.10/site-packages/transformers/generation/utils.py", line 1622, in generate
    result = self._sample(
  File "/home/ubuntu/anaconda3/envs/env/lib/python3.10/site-packages/transformers/generation/utils.py", line 2829, in _sample
    next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

whycantfindaname commented 2 weeks ago

the same problem, have you fixed it?

whycantfindaname commented 2 weeks ago

@czczup Could you please have a look at this problem? 能麻烦作者看一下这个问题吗，我用自定义数据finetune完推理时也是报这个错，然后如果加上logit_processor会输出乱码

from transformers.generation.logits_process import LogitsProcessor, LogitsProcessorList
from transformers.generation.logits_process import InfNanRemoveLogitsProcessor, MinLengthLogitsProcessor

logits_processor = LogitsProcessorList()
logits_processor.append(MinLengthLogitsProcessor(15, eos_token_id=tokenizer.eos_token_id))
logits_processor.append(InfNanRemoveLogitsProcessor())

TimeOverflow commented 1 week ago

This issue can solve your problem. After Lora finetuning, you need to merge the weights.

OpenGVLab / InternVL