great work but a little problem:
model_path="./checkpoints/cora.3/llaga-vicuna-7b-simteg-2-10-linear-projector_nc-lp"
model_base="lmsys/vicuna-7b-v1.5-16k" #meta-llama/Llama-2-7b-hf
mode="v1" # use 'llaga_llama_2' for llama and "v1" for others
dataset="cora" #test dataset
task="nc" #test task
emb="simteg"
use_hop=4
sample_size=10
template="HO" # or ND
output_path="/home/bjf/LLaGA/checkpoints"
/home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:68: UserWarning: An issue occurred while importing 'pyg-lib'. Disabling its usage. Stacktrace: /lib/x86_64-linux-gnu/libm.so.6: version GLIBC_2.29' not found (required by /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/libpyg.so) warnings.warn(f"An issue occurred while importing 'pyg-lib'. " /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:86: UserWarning: An issue occurred while importing 'torch-scatter'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_scatter/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn(f"An issue occurred while importing 'torch-scatter'. " /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:97: UserWarning: An issue occurred while importing 'torch-cluster'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_cluster/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn(f"An issue occurred while importing 'torch-cluster'. " /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:113: UserWarning: An issue occurred while importing 'torch-spline-conv'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_spline_conv/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn( /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:124: UserWarning: An issue occurred while importing 'torch-sparse'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_sparse/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn(f"An issue occurred while importing 'torch-sparse'. " Loaded from /home/bjf/LLaGA/checkpoints/cora.3/llaga-vicuna-7b-simteg-2-10-linear-projector_nc-lp. Model Base: lmsys/vicuna-7b-v1.5-16k Loading LLaGA from base model... Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]/home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/transformers/modeling_utils.py:460: FutureWarning: You are usingtorch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. return torch.load(checkpoint_file, map_location="cpu") Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████| 2/2 [00:09<00:00, 4.57s/it] Some weights of LlagaLlamaForCausalLM were not initialized from the model checkpoint at lmsys/vicuna-7b-v1.5-16k and are newly initialized: ['model.mm_projector.weight', 'model.mm_projector.bias'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. /home/bjf/LLaGA/./model/builder.py:108: FutureWarning: You are usingtorch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. mm_projector_weights = torch.load(os.path.join(model_path, 'mm_projector.bin'), map_location='cpu') Load from local path You shouldn't move a model that is dispatched using accelerate hooks. /home/bjf/LLaGA/eval/eval_pretrain.py:108: FutureWarning: You are usingtorch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
data = torch.load(data_path)
Load from dataset/cora/sampled_2_10_test.jsonl
Traceback (most recent call last):
File "/home/bjf/LLaGA/eval/eval_pretrain.py", line 325, in
eval_model(args)
File "/home/bjf/LLaGA/eval/eval_pretrain.py", line 122, in eval_model
line_number = len(open(answers_file, 'r').readlines())
IsADirectoryError: [Errno 21] Is a directory: '/home/bjf/LLaGA/checkpoints'
no matter how i gear the path ,it report this error
great work but a little problem: model_path="./checkpoints/cora.3/llaga-vicuna-7b-simteg-2-10-linear-projector_nc-lp" model_base="lmsys/vicuna-7b-v1.5-16k" #meta-llama/Llama-2-7b-hf mode="v1" # use 'llaga_llama_2' for llama and "v1" for others dataset="cora" #test dataset task="nc" #test task emb="simteg" use_hop=4 sample_size=10 template="HO" # or ND output_path="/home/bjf/LLaGA/checkpoints"
python eval/eval_pretrain.py \ --model_path ${model_path} \ --model_base ${model_base} \ --conv_mode ${mode} \ --dataset ${dataset} \ --pretrained_embedding_type ${emb} \ --use_hop ${use_hop} \ --sample_neighbor_size ${sample_size} \ --answers_file ${output_path} \ --task ${task} \ --cache_dir ../checkpoint \ --template ${template}
/home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:68: UserWarning: An issue occurred while importing 'pyg-lib'. Disabling its usage. Stacktrace: /lib/x86_64-linux-gnu/libm.so.6: version
GLIBC_2.29' not found (required by /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/libpyg.so) warnings.warn(f"An issue occurred while importing 'pyg-lib'. " /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:86: UserWarning: An issue occurred while importing 'torch-scatter'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_scatter/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn(f"An issue occurred while importing 'torch-scatter'. " /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:97: UserWarning: An issue occurred while importing 'torch-cluster'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_cluster/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn(f"An issue occurred while importing 'torch-cluster'. " /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:113: UserWarning: An issue occurred while importing 'torch-spline-conv'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_spline_conv/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn( /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_geometric/typing.py:124: UserWarning: An issue occurred while importing 'torch-sparse'. Disabling its usage. Stacktrace: /home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/torch_sparse/_version_cuda.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev warnings.warn(f"An issue occurred while importing 'torch-sparse'. " Loaded from /home/bjf/LLaGA/checkpoints/cora.3/llaga-vicuna-7b-simteg-2-10-linear-projector_nc-lp. Model Base: lmsys/vicuna-7b-v1.5-16k Loading LLaGA from base model... Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]/home/bjf/anaconda3/envs/llaga/lib/python3.10/site-packages/transformers/modeling_utils.py:460: FutureWarning: You are using
torch.loadwith
weights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for
weights_onlywill be flipped to
True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via
torch.serialization.add_safe_globals. We recommend you start setting
weights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. return torch.load(checkpoint_file, map_location="cpu") Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████| 2/2 [00:09<00:00, 4.57s/it] Some weights of LlagaLlamaForCausalLM were not initialized from the model checkpoint at lmsys/vicuna-7b-v1.5-16k and are newly initialized: ['model.mm_projector.weight', 'model.mm_projector.bias'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. /home/bjf/LLaGA/./model/builder.py:108: FutureWarning: You are using
torch.loadwith
weights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for
weights_onlywill be flipped to
True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via
torch.serialization.add_safe_globals. We recommend you start setting
weights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. mm_projector_weights = torch.load(os.path.join(model_path, 'mm_projector.bin'), map_location='cpu') Load from local path You shouldn't move a model that is dispatched using accelerate hooks. /home/bjf/LLaGA/eval/eval_pretrain.py:108: FutureWarning: You are using
torch.loadwith
weights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for
weights_onlywill be flipped to
True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via
torch.serialization.add_safe_globals. We recommend you start setting
weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. data = torch.load(data_path) Load from dataset/cora/sampled_2_10_test.jsonlTraceback (most recent call last): File "/home/bjf/LLaGA/eval/eval_pretrain.py", line 325, in
eval_model(args)
File "/home/bjf/LLaGA/eval/eval_pretrain.py", line 122, in eval_model
line_number = len(open(answers_file, 'r').readlines())
IsADirectoryError: [Errno 21] Is a directory: '/home/bjf/LLaGA/checkpoints'
no matter how i gear the path ,it report this error