InternLM / InternLM/lmdeploy

[Bug] 使用internlm2-chat-7b 微调后的自制模型,4bit量化后无法使用

Open
#1,109 11 comments 0 reactions 1 assignee Claimed by @pppppM View on GitHub
Dominant language
Python
Stars
8.1k
Forks
748
Avg merge
6d 2h
Merged PRs (30d)
54

Description

### 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.

### Describe the bug

我自制了一个基于internlm2-chat-7b的食谱模型 zhanghuiATchina/zhangxiaobai_shishen2_full

https://www.modelscope.cn/models/zhanghuiATchina/zhangxiaobai_shishen2_full/summary

运行良好。

现考虑将它进行4bit量化。
但是量化后的模型无法使用

### Reproduction

操作过程如下:

conda activate lmdeploynew
cd ~/shishen2-full
lmdeploy lite auto_awq ./merged --w-bits 4 --w-group-size 128 --work-dir ./merged-4bit --calib-dataset c4
正常完成。生成的目录如下:
3f771049b2afe49f2ef5dfd34e56e62

现在无论是用 xtuner chat还是用 lmdeploy chat都无法正常完成对话:

xtuner verision: 0.1.13
65629cae7460a33e2933dff9c35dae1

xtuner chat现象如下:
xtuner chat ./merged-4bit --prompt-template internlm2_chat --temperature 0.8 --top-p 0.8 --repetition-penalty 1.002
启动的时候会卡住半天,然后:
7b45c3955a2ab6f10c714711ba57a0b

f10d8bb7c534965b550111f344ffc89

输入 小笼包怎么做?
就变成这样子了:
44f48a2296f8174863e05143aac7805

xtuner chat ./merged-4bit --bits 4 --temperature 0.8 --top-p 0.8 --repetition-penalty 1.002 --prompt-template internlm2_chat
启动的时候会卡住半天,然后:
cb60d04427d390a8fc3c8216c4c926f

63853c0a8aa28d71d72eee90dc04e62

输入 小笼包怎么做?
就变成这样子了:
b17b8fd02f74f32275b21dea98deedb

附:
原始模型对话:
xtuner chat ./merged --bits 4 --temperature 0.8 --top-p 0.8 --repetition-penalty 1.002 --prompt-template internlm2_chat
55fdfa2f14b585826b1470e2a095a5e

### Environment

```Shell
(lmdeploynew) zhanghui@zhanghui:~/shishen2-full$ lmdeploy check_env
/home/zhanghui/anaconda3/envs/lmdeploynew/lib/python3.10/site-packages/fuzzywuzzy/fuzz.py:11: UserWarning: Using slow pure-python SequenceMatcher. Install python-Levenshtein to remove this warning
warnings.warn('Using slow pure-python SequenceMatcher. Install python-Levenshtein to remove this warning')
sys.platform: linux
Python: 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 3080 Laptop GPU
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.6, V11.6.124
GCC: gcc (Ubuntu 9.5.0-1ubuntu1~22.04) 9.5.0
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: AVX512
- 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 8.5 (built against CUDA 11.7)
- Built with 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,

LMDeploy: 0.2.1+
transformers: 4.37.1
gradio: 3.50.2
fastapi: 0.109.0
pydantic: 2.5.3
(lmdeploynew) zhanghui@zhanghui:~/shishen2-full$
```

### Error traceback

_No response_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.