allanraventos
commented
2 months ago Getting the same error with agent
Open Shawnzheng011019 opened 2 months ago
allanraventos
commented
2 months ago Getting the same error with agent
System Info / 系統信息
SwissArmyTransformer>=0.4.9 transformers>=4.36.2 xformers>=0.0.22 torch>=2.1.0 torchvision>=0.16.2 spacy>=3.6.0 pillow>=10.2.0 deepspeed>=0.13.1 seaborn>=0.13.2 loguru~=0.7.2 streamlit>=1.31.0 timm>=0.9.12 accelerate>=0.26.1 pydantic>=2.6.0
for openai demo
openai>=1.16.0 sse-starlette>=1.8.2 fastapi>=0.110.1 httpx>=0.27.0 uvicorn>=0.29.0 jsonlines>=4.0.0
Who can help? / 谁可以帮助到您？
@zRzRzRzRzRzRzR 请问以下报错如何解决，是否是读取图片路径时的问题： image path >>>>> /workspace/CogVLM-chat/test.png Human:图片里面包含什么内容 /root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/bitsandbytes/nn/modules.py:426: UserWarning: Input type into Linear4bit is torch.float16, but bnb_4bit_compute_dtype=torch.float32 (default). This will lead to slow inference or training speed. warnings.warn( Traceback (most recent call last): File "cli_demo_hf.py", line 98, in
outputs = model.generate(inputs, gen_kwargs)
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, kwargs)
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/transformers/generation/utils.py", line 1914, in generate
result = self._sample(
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/transformers/generation/utils.py", line 2651, in _sample
outputs = self(
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, kwargs)
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/accelerate/hooks.py", line 166, in new_forward
output = module._old_forward(*args, kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/cogvlm-chat-hf/modeling_cogvlm.py", line 660, in forward
outputs = self.model(
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, kwargs)
File "/root/miniconda3/envs/cogvlm/lib/python3.8/site-packages/accelerate/hooks.py", line 166, in new_forward
output = module._old_forward(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/cogvlm-chat-hf/modeling_cogvlm.py", line 442, in forward
return self.llm_forward(
File "/root/.cache/huggingface/modules/transformers_modules/cogvlm-chat-hf/modeling_cogvlm.py", line 491, in llm_forward
past_key_values_length = past_key_values[0][0].shape[2]
AttributeError: 'str' object has no attribute 'shape'
Information / 问题信息
Reproduction / 复现过程
python cli_demo_hf.py --from_pretrained /workspace/CogVLM-chat/models/cogvlm-chat-hf --fp16 --quant 4
Expected behavior / 期待表现
在openaiapi或终端调用时能够成功读取图片