llava-hf

/

vip-llava-7b-hf

like 12

Hello. I am trying to run the code provided in the model card and it is throwing the above error

python - 3.10
transformers - 4.39.1

CODE

import requests
from PIL import Image

import torch
from transformers import AutoProcessor, VipLlavaForConditionalGeneration

model_id = "llava-hf/vip-llava-7b-hf"

question = "What are these?"
prompt = f"A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: \n{question}###Assistant:"

image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"

model = VipLlavaForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=torch.float16,
low_cpu_mem_usage=True,
).to(0)

processor = AutoProcessor.from_pretrained(model_id)

raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))

FULL ERROR

Traceback (most recent call last):
File "/project/kkoshti/clembench/../inferences/vipllava.py", line 26, in
output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/transformers/generation/utils.py", line 1527, in generate
result = self._greedy_search(
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/transformers/generation/utils.py", line 2411, in _greedy_search
outputs = self(
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/transformers/models/vipllava/modeling_vipllava.py", line 473, in forward
outputs = self.language_model(
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 1196, in forward
outputs = self.model(
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 1016, in forward
layer_outputs = decoder_layer(
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 739, in forward
hidden_states, self_attn_weights, present_key_value = self.self_attn(
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/project/kkoshti/envs/clem/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 670, in forward
attn_output = torch.nn.functional.scaled_dot_product_attention(
RuntimeError: The expanded size of the tensor (625) must match the existing size (129) at non-singleton dimension 3. Target sizes: [1, 32, 1, 625]. Tensor sizes: [1, 1, 1, 129]

The same type of error is produced after using the pipeline code as well.