Closed Barbery closed 3 months ago
check你的显卡和驱动
@zRzRzRzRzRzRzR
torch_dtype=torch.bfloat16,
这个,哪里还需要改动吗?NVIDIA-SMI 550.54.15 Driver Version: 550.54.15 CUDA Version: 12.4 |
那看上去这个环境是没有问题的,卡是支持bloat16的吧。给个环境我在check一下
@zRzRzRzRzRzRzR 显卡是3090 应该支持bfloat16的。你说的给个环境是具体还需要提供什么信息?我没搞明白,抱歉。
就是python包的环境,现在显卡和驱动看上去没有问题了
@zRzRzRzRzRzRzR
# pip list
Package Version
---------------------------- ---------------------
absl-py 1.4.0
accelerate 0.26.1
aiofiles 23.1.0
aiohttp 3.9.2
aiosignal 1.3.1
altair 4.2.2
annotated-types 0.6.0
anyio 4.2.0
appdirs 1.4.4
appnope 0.1.3
argon2-cffi 23.1.0
argon2-cffi-bindings 21.2.0
arxiv 2.1.0
asgiref 3.7.2
asrt-sdk 1.2.0
astor 0.8.1
asttokens 2.4.1
astunparse 1.6.3
async-timeout 4.0.3
async-tio 1.3.2
attrs 23.2.0
bcrypt 4.0.1
beautifulsoup4 4.12.2
blinker 1.7.0
boltons 23.0.0
brotlipy 0.7.0
bs4 0.0.1
cached-property 1.5.2
cachetools 5.3.1
certifi 2023.11.17
cffi 1.16.0
chardet 5.1.0
charset-normalizer 3.3.2
chatgptpy 1.0.8
chex 0.1.85
click 8.1.7
cmake 3.26.3
colorama 0.4.6
colorcet 3.1.0
comm 0.2.1
conda 23.3.1
conda-content-trust 0.1.3
conda-package-handling 2.0.2
conda_package_streaming 0.7.0
contourpy 1.0.7
cpm-kernels 1.0.11
cryptography 39.0.1
cssselect2 0.7.0
curl-cffi 0.5.6
cycler 0.11.0
Cython 0.29.35
dataclasses-json 0.6.3
datasets 2.12.0
DateTime 5.4
debugpy 1.8.0
decorator 5.1.1
derpconf 0.8.3
dill 0.3.6
distro 1.9.0
Django 4.1.9
django-crontab 0.7.1
django-environ 0.10.0
dlib 19.24.2
docker 6.1.2
docker-compose 1.29.2
docker-pycreds 0.4.0
dockerpty 0.4.1
docopt 0.6.2
docx2txt 0.8
easy_install 66.0.2
einops 0.8.0
entrypoints 0.4
environs 9.5.0
etils 1.6.0
exceptiongroup 1.2.0
executing 2.0.1
ez_setup 0.9
face-recognition 1.3.0
face-recognition-models 0.3.0
fastapi 0.109.0
feedparser 6.0.10
ffmpeg-python 0.2.0
ffmpy 0.3.0
filelock 3.13.1
flash-attn 2.5.9.post1
Flask 3.0.2
flatbuffers 23.5.26
flax 0.6.4
fonttools 4.39.4
frozenlist 1.4.1
fsspec 2023.12.2
future 0.18.3
gast 0.4.0
gensim 4.3.1
gitdb 4.0.10
GitPython 3.1.31
google-auth 2.19.0
google-auth-oauthlib 0.4.6
google-pasta 0.2.0
googleapis-common-protos 1.59.0
gradio 4.14.0
gradio_client 0.8.0
greenlet 3.0.3
grpcio 1.58.0
grpcio-tools 1.54.2
h11 0.14.0
h5py 3.8.0
httpcore 1.0.4
httplib2 0.22.0
httpx 0.27.0
huggingface-hub 0.23.4
idna 3.6
imageio 2.31.0
imageio-ffmpeg 0.4.8
importlib-metadata 7.0.1
importlib-resources 6.1.1
ipykernel 6.29.0
ipython 8.18.1
itsdangerous 2.1.2
jax 0.4.23
jaxlib 0.4.23+cuda12.cudnn89
jedi 0.19.1
jieba 0.42.1
Jinja2 3.1.3
joblib 1.3.2
jsonpatch 1.33
jsonpointer 2.4
jsonschema 3.2.0
jupyter_client 8.6.0
jupyter_core 5.7.1
keras 2.8.0
Keras-Preprocessing 1.1.2
kiwisolver 1.4.4
langchain 0.1.1
langchain-community 0.0.13
langchain-core 0.1.12
langchainhub 0.1.14
langsmith 0.0.82
latex2mathml 3.77.0
libclang 16.0.0
libthumbor 2.0.2
linkify-it-py 2.0.2
lit 16.0.5
llvmlite 0.40.0
loguru 0.7.2
lxml 4.9.3
Markdown 3.4.3
markdown-it-py 2.2.0
MarkupSafe 2.1.4
marshmallow 3.20.2
matplotlib 3.7.1
matplotlib-inline 0.1.6
mdit-py-plugins 0.3.3
mdtex2html 1.2.0
mdurl 0.1.2
milvus 2.3.5
minio 7.2.3
mkl-fft 1.3.6
mkl-random 1.2.2
mkl-service 2.4.0
ml-dtypes 0.3.2
more-itertools 9.1.0
moviepy 1.0.3
mpmath 1.3.0
msgpack 1.0.7
multidict 6.0.4
multiprocess 0.70.14
mypy-extensions 1.0.0
mysql 0.0.3
mysql-connector-python 8.1.0
mysqlclient 2.2.0
nest-asyncio 1.6.0
networkx 3.2.1
nltk 3.8.1
numba 0.57.0
numpy 1.26.3
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
nvidia-cuda-nvcc-cu12 12.4.131
nvidia-cuda-nvrtc-cu12 12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12 8.9.2.26
nvidia-cufft-cu12 11.0.2.54
nvidia-curand-cu12 10.3.2.106
nvidia-cusolver-cu12 11.4.5.107
nvidia-cusparse-cu12 12.1.0.106
nvidia-nccl-cu12 2.18.1
nvidia-nvjitlink-cu12 12.4.127
nvidia-nvtx-cu12 12.1.105
oauthlib 3.2.2
openai 1.13.3
openai-whisper 20230314
OpenAIAuth 3.0.0
opencv-python 4.7.0.72
opencv-python-headless 4.7.0.72
opt-einsum 3.3.0
optax 0.1.7
orbax 0.1.9
orbax-checkpoint 0.4.8
orjson 3.9.15
packaging 23.2
paddle-bfloat 0.1.2
paddlepaddle-gpu 2.3.0
pandas 2.2.0
paramiko 3.1.0
parrots 0.1.7
parso 0.8.3
pathtools 0.1.2
peft 0.3.0
pexpect 4.9.0
piexif 1.1.3
pillow 10.2.0
pip 24.1
platformdirs 4.1.0
pluggy 1.0.0
pocketsphinx 5.0.1
proglog 0.1.10
progressbar 2.5
prompt-toolkit 3.0.43
protobuf 4.25.2
psutil 5.9.8
ptyprocess 0.7.0
pure-eval 0.2.2
pyarrow 15.0.0
pyasn1 0.5.0
pyasn1-modules 0.3.0
pycosat 0.6.4
pycparser 2.21
pycryptodome 3.20.0
pycurl 7.45.2
pydantic 2.5.3
pydantic_core 2.14.6
pydash 7.0.4
pydeck 0.8.1b0
pydub 0.25.1
Pygments 2.17.2
PyJWT 2.8.0
pymilvus 2.3.5
Pympler 1.0.1
PyMySQL 1.1.0
PyNaCl 1.5.0
pyOpenSSL 23.0.0
pyparsing 3.0.9
pypinyin 0.49.0
pyrsistent 0.19.3
PySocks 1.7.1
pysrt 1.1.2
python-dateutil 2.8.2
python-dotenv 1.0.1
python-multipart 0.0.6
python-speech-features 0.6
python-utils 3.6.0
pytorch-triton 2.1.0+440fd1bf20
pytz 2023.3.post1
pytz-deprecation-shim 0.1.0.post0
PyYAML 6.0.1
pyzmq 25.1.2
regex 2023.12.25
reportlab 4.0.4
requests 2.31.0
requests-oauthlib 1.3.1
responses 0.18.0
result 0.16.1
revChatGPT 6.8.6
rich 13.4.1
rouge 1.0.1
rouge-chinese 1.0.3
rsa 4.9
ruamel.yaml 0.17.21
ruamel.yaml.clib 0.2.6
sacremoses 0.0.53
safetensors 0.4.2
scikit-learn 1.4.0
scipy 1.12.0
seaborn 0.13.2
semantic-version 2.10.0
sentence-transformers 3.0.1
sentencepiece 0.1.99
sentry-sdk 1.24.0
setproctitle 1.3.2
setuptools 69.5.1
setuptools-rust 1.6.0
sgmllib3k 1.0.0
shellingham 1.5.4
six 1.16.0
smart-open 6.3.0
smmap 5.0.0
sniffio 1.3.0
socksio 1.0.0
sounddevice 0.4.6
SoundFile 0.9.0.post1
soupsieve 2.4.1
speech-recognition-fork 3.8.1.2021.6.14
SpeechRecognition 3.10.0
SQLAlchemy 2.0.25
sqlparse 0.4.4
sse-starlette 1.8.2
stack-data 0.6.3
starlette 0.35.1
statsd 3.3.0
streamlit 1.30.0
streamlit-chat 0.0.2.2
svglib 1.5.1
sympy 1.12
tenacity 8.2.3
tensorboard 2.8.0
tensorboard-data-server 0.6.1
tensorboard-plugin-wit 1.8.1
tensorboardX 2.6
tensorflow 2.8.0
tensorflow-estimator 2.12.0
tensorflow-io-gcs-filesystem 0.32.0
tensorstore 0.1.52
termcolor 2.3.0
text2vec 1.1.8
textgen 0.2.5
texttable 1.6.7
tf-estimator-nightly 2.8.0.dev2021122109
threadpoolctl 3.2.0
thumbor 7.4.7
thumbor-plugins-gifv 0.1.2
tiktoken 0.5.2
timm 0.9.12
tinycss2 1.2.1
tls-client 0.2.1
tokenizers 0.19.1
toml 0.10.2
tomli 2.0.1
tomlkit 0.12.0
toolz 0.12.0
torch 2.1.2
torchvision 0.16.2
tornado 6.4
tqdm 4.66.1
traitlets 5.14.1
transformer-utils 0.1.1
transformers 4.41.2
trash-cli 0.23.11.10
triton 2.1.0
turtle 0.0.1
typer 0.9.0
types-requests 2.31.0.20240106
typing_extensions 4.9.0
typing-inspect 0.9.0
tzdata 2023.4
tzlocal 4.3.1
uc-micro-py 1.0.2
ujson 5.9.0
uritemplate 4.1.1
urllib3 2.1.0
uvicorn 0.26.0
validators 0.20.0
wandb 0.15.3
watchdog 3.0.0
Wave 0.0.2
wcwidth 0.2.13
webcolors 1.11.1
webencodings 0.5.1
websocket-client 0.59.0
websockets 11.0.3
Werkzeug 3.0.1
wheel 0.38.4
whisper_jax 0.0.1
wrapt 1.14.1
xxhash 3.2.0
yapf 0.40.2
yarl 1.9.4
zhconv 1.4.3
zhipuai 2.0.1
zipp 3.17.0
zope.interface 6.2
zstandard 0.19.0
transformers 4.40.2 试试 torch 2.3.0
@zRzRzRzRzRzRzR 还是和之前一样,乱输出
包安装情况
# pip install transformers==4.40.2 torch==2.3.0
Looking in indexes: https://mirrors.cloud.tencent.com/pypi/simple
Requirement already satisfied: transformers==4.40.2 in /root/miniconda3/lib/python3.10/site-packages (4.40.2)
Requirement already satisfied: torch==2.3.0 in /root/miniconda3/lib/python3.10/site-packages (2.3.0)
Requirement already satisfied: filelock in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (3.13.1)
Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (0.23.4)
Requirement already satisfied: numpy>=1.17 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (1.26.3)
Requirement already satisfied: packaging>=20.0 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (23.2)
Requirement already satisfied: pyyaml>=5.1 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (6.0.1)
Requirement already satisfied: regex!=2019.12.17 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (2023.12.25)
Requirement already satisfied: requests in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (2.31.0)
Requirement already satisfied: tokenizers<0.20,>=0.19 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (0.19.1)
Requirement already satisfied: safetensors>=0.4.1 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (0.4.2)
Requirement already satisfied: tqdm>=4.27 in /root/miniconda3/lib/python3.10/site-packages (from transformers==4.40.2) (4.66.1)
Requirement already satisfied: typing-extensions>=4.8.0 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (4.9.0)
Requirement already satisfied: sympy in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (1.12)
Requirement already satisfied: networkx in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (3.2.1)
Requirement already satisfied: jinja2 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (3.1.3)
Requirement already satisfied: fsspec in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (2023.12.2)
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (12.1.105)
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (12.1.105)
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (12.1.105)
Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (8.9.2.26)
Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (12.1.3.1)
Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (11.0.2.54)
Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (10.3.2.106)
Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (11.4.5.107)
Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (12.1.0.106)
Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (2.20.5)
Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (12.1.105)
Requirement already satisfied: triton==2.3.0 in /root/miniconda3/lib/python3.10/site-packages (from torch==2.3.0) (2.3.0)
Requirement already satisfied: nvidia-nvjitlink-cu12 in /root/miniconda3/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.3.0) (12.4.127)
Requirement already satisfied: MarkupSafe>=2.0 in /root/miniconda3/lib/python3.10/site-packages (from jinja2->torch==2.3.0) (2.1.4)
Requirement already satisfied: charset-normalizer<4,>=2 in /root/miniconda3/lib/python3.10/site-packages (from requests->transformers==4.40.2) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /root/miniconda3/lib/python3.10/site-packages (from requests->transformers==4.40.2) (3.6)
Requirement already satisfied: urllib3<3,>=1.21.1 in /root/miniconda3/lib/python3.10/site-packages (from requests->transformers==4.40.2) (2.1.0)
Requirement already satisfied: certifi>=2017.4.17 in /root/miniconda3/lib/python3.10/site-packages (from requests->transformers==4.40.2) (2023.11.17)
Requirement already satisfied: mpmath>=0.19 in /root/miniconda3/lib/python3.10/site-packages (from sympy->torch==2.3.0) (1.3.0)
那确实排查不出问题了,没有遇到这种情况,或许要重新拉一次模型,配置文件等都是最新的
generate_kwargs = { "input_ids": model_inputs, "streamer": streamer, "max_new_tokens": max_length, "do_sample": True, "top_p": top_p, "temperature": temperature, "stopping_criteria": StoppingCriteriaList([stop]), "repetition_penalty": 1.2, "eos_token_id": model.config.eos_token_id, } 这样子呢,参考basic_demo/trans_cli_demo.py
我把github的仓库clone下来,跑了basic_demo/trans_cli_demo.py这个脚本也一样,还是胡乱输出。
@zRzRzRzRzRzRzR 结贴,最后重新拉了一遍模型后,正常工作了
System Info / 系統信息
代码是readme中的示例代码,具体如下:
输出结果:
Who can help? / 谁可以帮助到您?
No response
Information / 问题信息
Reproduction / 复现过程
运行上述脚本
Expected behavior / 期待表现
期待正常回复