Closed KiwiHana closed 5 months ago
Run the example normally and cannot get same error with following python package list:
Sync python package list offline and will try to rerun example again after reply.
here is the pip list: @lalalapotter @KiwiHana
Package Version
----------------------------- --------------------
absl-py 2.0.0
accelerate 0.21.0
addict 2.4.0
aiohttp 3.9.1
aiosignal 1.3.1
annotated-types 0.6.0
antlr4-python3-runtime 4.9.3
apturl 0.5.2
async-timeout 4.0.3
attrs 23.2.0
audioread 3.0.1
bcrypt 3.2.0
bigdl-core-xe-21 2.5.0b20240311
bigdl-core-xe-esimd-21 2.5.0b20240311
bigdl-llm 2.5.0b20240311
bitsandbytes 0.43.0
blinker 1.4
Brlapi 0.8.3
cachetools 5.3.2
certifi 2020.6.20
cffi 1.16.0
chardet 4.0.0
charset-normalizer 3.3.2
click 8.1.7
colorama 0.4.4
command-not-found 0.3
contourpy 1.2.0
cryptography 3.4.8
cupshelpers 1.0
cycler 0.12.1
datasets 2.16.1
dbus-python 1.2.18
decorator 5.1.1
defer 1.0.6
defusedxml 0.7.1
dill 0.3.7
distro 1.7.0
distro-info 1.1build1
duplicity 0.8.21
einops 0.7.0
evaluate 0.4.1
fasteners 0.14.1
filelock 3.13.1
fonttools 4.45.0
frozenlist 1.4.1
fsspec 2023.10.0
future 0.18.2
google-auth 2.23.4
google-auth-oauthlib 1.1.0
grpcio 1.59.3
httplib2 0.20.2
huggingface-hub 0.21.4
idna 3.3
importlib-metadata 4.6.4
intel-extension-for-pytorch 2.1.10+xpu
intel-openmp 2024.0.2
iotop 0.6
jeepney 0.7.1
Jinja2 3.1.2
jiwer 3.0.3
joblib 1.3.2
jstyleson 0.0.2
keyring 23.5.0
kiwisolver 1.4.5
language-selector 0.1
launchpadlib 1.10.16
lazr.restfulclient 0.14.4
lazr.uri 1.0.6
lazy_loader 0.3
librosa 0.10.1
llvmlite 0.41.1
lockfile 0.12.2
louis 3.20.0
macaroonbakery 1.3.1
Mako 1.1.3
Markdown 3.5.1
MarkupSafe 2.1.3
matplotlib 3.8.3
monotonic 1.6
more-itertools 8.10.0
mpmath 1.3.0
msgpack 1.0.7
multidict 6.0.4
multiprocess 0.70.15
netifaces 0.11.0
networkx 3.2.1
numba 0.58.1
numpy 1.26.3
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
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 12.3.101
nvidia-nvtx-cu12 12.1.105
oauthlib 3.2.0
olefile 0.46
omegaconf 2.3.0
onnx 1.15.0
opencv-python 4.8.1.78
openvino 2023.2.0
openvino-dev 2023.2.0
openvino-telemetry 2023.2.1
packaging 23.2
pandas 2.1.4
paramiko 2.9.3
pexpect 4.8.0
pillow 10.2.0
pip 23.3.1
platformdirs 4.1.0
pooch 1.8.0
protobuf 4.25.1
psutil 5.9.7
ptyprocess 0.7.0
py-cpuinfo 9.0.0
pyarrow 14.0.2
pyarrow-hotfix 0.6
pyasn1 0.5.1
pyasn1-modules 0.3.0
pycairo 1.20.1
pycparser 2.21
pycups 2.0.1
pydantic 2.5.3
pydantic_core 2.14.6
PyGObject 3.42.1
PyJWT 2.3.0
pymacaroons 0.13.0
PyNaCl 1.5.0
pyparsing 2.4.7
pyRFC3339 1.1
python-apt 2.4.0+ubuntu1
python-dateutil 2.8.2
python-debian 0.1.43ubuntu1
pytz 2022.1
pyxdg 0.27
PyYAML 5.4.1
rapidfuzz 3.6.1
regex 2023.12.25
reportlab 3.6.8
requests 2.31.0
requests-oauthlib 1.3.1
responses 0.18.0
rsa 4.9
safetensors 0.4.2
scikit-learn 1.3.2
scipy 1.11.4
seaborn 0.13.0
SecretStorage 3.3.1
sentencepiece 0.1.99
setuptools 59.6.0
six 1.16.0
soundfile 0.12.1
soxr 0.3.7
ssh-import-id 5.11
sympy 1.12
systemd-python 234
tabulate 0.9.0
tensorboard 2.16.2
tensorboard-data-server 0.7.2
texttable 1.7.0
thefuzz 0.20.0
thop 0.1.1.post2209072238
threadpoolctl 3.2.0
tiktoken 0.5.2
tokenizers 0.13.3
torch 2.1.0a0+cxx11.abi
torchvision 0.16.0a0+cxx11.abi
tqdm 4.66.1
transformers 4.31.0
transformers-stream-generator 0.0.4
triton 2.1.0
typing_extensions 4.8.0
tzdata 2023.3
ubuntu-advantage-tools 8001
ubuntu-drivers-common 0.0.0
ufw 0.36.1
unattended-upgrades 0.1
urllib3 1.26.5
usb-creator 0.3.7
wadllib 1.3.6
Werkzeug 3.0.1
wheel 0.41.2
xdg 5
xkit 0.0.0
xxhash 3.4.1
yarl 1.9.4
zipp 3.17.0
修改以下两句代码后,cpu 32G memory可以运行了。但是同样的图片和文字,这种方式的回答结果跟示例有差距,检测物体框还报错了。 model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cpu", trust_remote_code=True, fp16=True) model = optimize_model(model, low_bit='sym_int4', modules_to_not_convert=['c_fc', 'out_proj']) model = model.half().to('xpu')
2024-03-15 13:12:27,135 - INFO - intel_extension_for_pytorch auto imported
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [02:55<00:00, 17.57s/it]
2024-03-15 13:15:23,291 - INFO - Converting the current model to sym_int4 format......
-------------------- Session 1 --------------------
Please input a picture: http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg
Please enter the text: 这是什么?
---------- Response ----------
这张照片似乎是在太空中拍摄的地球,但实际上是由于视觉错觉效果,许多玩具熊被聚集在一起形成了一个圆形的图案。
-------------------- Session 2 --------------------
Please input a picture:
Please enter the text: 这个小女孩多大了?
---------- Response ----------
根据图片内容,这个小女孩似乎只有幼儿园或者小学年龄,具体年龄不得而知。
-------------------- Session 3 --------------------
Please input a picture:
Please enter the text: 在图中检测框出玩具熊
Traceback (most recent call last):
File "/home/a770/kiwi/qwen-vl/chat.py", line 92, in <module>
response, history = model.chat(tokenizer, query = query, history = history)
File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 947, in chat
outputs = self.generate(
File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 1066, in generate
return super().generate(
File "/home/a770/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/generation/utils.py", line 1588, in generate
return self.sample(
File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/generation/utils.py", line 2642, in sample
outputs = self(
File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 856, in forward
transformer_outputs = self.transformer(
File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 565, in forward
images = self.visual.encode(images)
File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/visual.py", line 420, in encode
image = Image.open(requests.get(image_path, stream=True).raw)
File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/PIL/Image.py", line 3309, in open
raise UnidentifiedImageError(msg)
PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7f0f16fca750>
如果使用INT4: model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, optimize_model=True,load_in_4bit=True).eval() 不能加载模型,报错如下:
(qwen-vl) a770@RPLP-A770:~/kiwi/qwen-vl$ python chat.py
/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/bitsandbytes/cextension.py:31: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
warn("The installed version of bitsandbytes was compiled without GPU support. "
/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32
/home/a770/.local/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: ''If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
warn(
2024-03-15 13:22:09,567 - INFO - intel_extension_for_pytorch auto imported
Traceback (most recent call last):
File "/home/a770/kiwi/qwen-vl/chat.py", line 41, in <module>
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, optimize_model=True,load_in_4bit=True).eval()
File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 488, in from_pretrained
return model_class.from_pretrained(
File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2297, in from_pretrained
raise RuntimeError("No GPU found. A GPU is needed for quantization.")
RuntimeError: No GPU found. A GPU is needed for quantization.
修改以下两句代码后,cpu 32G memory可以运行了。但是同样的图片和文字,这种方式的回答结果跟示例有差距,检测物体框还报错了。 model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cpu", trust_remote_code=True, fp16=True) model = optimize_model(model, low_bit='sym_int4', modules_to_not_convert=['c_fc', 'out_proj']) model = model.half().to('xpu')
2024-03-15 13:12:27,135 - INFO - intel_extension_for_pytorch auto imported Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [02:55<00:00, 17.57s/it] 2024-03-15 13:15:23,291 - INFO - Converting the current model to sym_int4 format...... -------------------- Session 1 -------------------- Please input a picture: http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg Please enter the text: 这是什么? ---------- Response ---------- 这张照片似乎是在太空中拍摄的地球,但实际上是由于视觉错觉效果,许多玩具熊被聚集在一起形成了一个圆形的图案。 -------------------- Session 2 -------------------- Please input a picture: Please enter the text: 这个小女孩多大了? ---------- Response ---------- 根据图片内容,这个小女孩似乎只有幼儿园或者小学年龄,具体年龄不得而知。 -------------------- Session 3 -------------------- Please input a picture: Please enter the text: 在图中检测框出玩具熊 Traceback (most recent call last): File "/home/a770/kiwi/qwen-vl/chat.py", line 92, in <module> response, history = model.chat(tokenizer, query = query, history = history) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 947, in chat outputs = self.generate( File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 1066, in generate return super().generate( File "/home/a770/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/generation/utils.py", line 1588, in generate return self.sample( File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/generation/utils.py", line 2642, in sample outputs = self( File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 856, in forward transformer_outputs = self.transformer( File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 565, in forward images = self.visual.encode(images) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/visual.py", line 420, in encode image = Image.open(requests.get(image_path, stream=True).raw) File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/PIL/Image.py", line 3309, in open raise UnidentifiedImageError(msg) PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7f0f16fca750>
For the Pillow error you may try following workaround:
# replace original code: image = Image.open(requests.get(image_path, stream=True).raw)
image = Image.open(io.BytesIO(requests.get(image_path, stream=True).content))
or you can check the version of following packages
pillow 10.2.0
requests 2.31.0
requests-oauthlib 1.3.1
Will further look into the abnormal reply.
如果使用INT4: model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, optimize_model=True,load_in_4bit=True).eval() 不能加载模型,报错如下:
(qwen-vl) a770@RPLP-A770:~/kiwi/qwen-vl$ python chat.py /home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/bitsandbytes/cextension.py:31: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable. warn("The installed version of bitsandbytes was compiled without GPU support. " /home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32 /home/a770/.local/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: ''If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source? warn( 2024-03-15 13:22:09,567 - INFO - intel_extension_for_pytorch auto imported Traceback (most recent call last): File "/home/a770/kiwi/qwen-vl/chat.py", line 41, in <module> model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, optimize_model=True,load_in_4bit=True).eval() File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 488, in from_pretrained return model_class.from_pretrained( File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2297, in from_pretrained raise RuntimeError("No GPU found. A GPU is needed for quantization.") RuntimeError: No GPU found. A GPU is needed for quantization.
You may try following command to check if there is GPU available.
import intel_extension_for_pytorch as ipex
import torch
torch.xpu.is_available()
修改以下两句代码后,cpu 32G memory可以运行了。但是同样的图片和文字,这种方式的回答结果跟示例有差距,检测物体框还报错了。 model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cpu", trust_remote_code=True, fp16=True) model = optimize_model(model, low_bit='sym_int4', modules_to_not_convert=['c_fc', 'out_proj']) model = model.half().to('xpu')
2024-03-15 13:12:27,135 - INFO - intel_extension_for_pytorch auto imported Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [02:55<00:00, 17.57s/it] 2024-03-15 13:15:23,291 - INFO - Converting the current model to sym_int4 format...... -------------------- Session 1 -------------------- Please input a picture: http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg Please enter the text: 这是什么? ---------- Response ---------- 这张照片似乎是在太空中拍摄的地球,但实际上是由于视觉错觉效果,许多玩具熊被聚集在一起形成了一个圆形的图案。 -------------------- Session 2 -------------------- Please input a picture: Please enter the text: 这个小女孩多大了? ---------- Response ---------- 根据图片内容,这个小女孩似乎只有幼儿园或者小学年龄,具体年龄不得而知。 -------------------- Session 3 -------------------- Please input a picture: Please enter the text: 在图中检测框出玩具熊 Traceback (most recent call last): File "/home/a770/kiwi/qwen-vl/chat.py", line 92, in <module> response, history = model.chat(tokenizer, query = query, history = history) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 947, in chat outputs = self.generate( File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 1066, in generate return super().generate( File "/home/a770/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/generation/utils.py", line 1588, in generate return self.sample( File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/transformers/generation/utils.py", line 2642, in sample outputs = self( File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 856, in forward transformer_outputs = self.transformer( File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/a770/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/modeling_qwen.py", line 565, in forward images = self.visual.encode(images) File "/home/a770/.cache/huggingface/modules/transformers_modules/Qwen-VL-Chat/visual.py", line 420, in encode image = Image.open(requests.get(image_path, stream=True).raw) File "/home/a770/miniconda3/envs/qwen-vl/lib/python3.10/site-packages/PIL/Image.py", line 3309, in open raise UnidentifiedImageError(msg) PIL.UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7f0f16fca750>
For the Pillow error you may try following workaround:
# replace original code: image = Image.open(requests.get(image_path, stream=True).raw) image = Image.open(io.BytesIO(requests.get(image_path, stream=True).content))
or you can check the version of following packages
pillow 10.2.0 requests 2.31.0 requests-oauthlib 1.3.1
Will further look into the abnormal reply.
根据提供的方法升级相关库,已解决,感谢!
https://github.com/intel-analytics/BigDL/tree/7a1a9edca7ebc1c02e155828f8475eb51cb8c06b/python/llm/example/GPU/PyTorch-Models/Model/qwen-vl
bigdl2.5.0b20240311 CPU memory:32G ADL+A770 因为32G内存无法加载模型,加载到9/10会killed,所以改成以下代码后能加载模型,但报错。 model = AutoModelForCausalLM.from_pretrained(model_path, device_map="cpu", trust_remote_code=True, fp16=True)
-------------------- Session 1 -------------------- Please input a picture: /home/test/Qwen/BigDL/examples/apple.jpeg Please enter the text: what is this? Traceback (most recent call last): File "/home/test/Qwen/BigDL/python/llm/example/GPU/PyTorch-Models/Model/qwen-vl/chat.py", line 92, in
response, history = model.chat(tokenizer, query = query, history = history)
File "/root/.cache/huggingface/modules/transformers_modules/modeling_qwen.py", line 947, in chat
outputs = self.generate(
File "/root/.cache/huggingface/modules/transformers_modules/modeling_qwen.py", line 1066, in generate
return super().generate(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 1588, in generate
return self.sample(
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 2642, in sample
outputs = self(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/modeling_qwen.py", line 856, in forward
transformer_outputs = self.transformer(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, *kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/modeling_qwen.py", line 565, in forward
images = self.visual.encode(images)
File "/root/.cache/huggingface/modules/transformers_modules/visual.py", line 426, in encode
return self(images)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/visual.py", line 410, in forward
x = self.attn_pool(x)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/visual.py", line 148, in forward
out = self.attn(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/activation.py", line 1241, in forward
attn_output, attn_output_weights = F.multi_head_attention_forward(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py", line 5300, in multi_head_attention_forward
q, k, v = _in_projection_packed(query, key, value, in_proj_weight, in_proj_bias)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py", line 4846, in _in_projection_packed
return linear(q, w_q, b_q), linear(k, w_k, b_k), linear(v, w_v, b_v)
RuntimeError: mat1 and mat2 must have the same dtype, but got Float and Half