Closed gsamaras closed 5 months ago
KimMeen
commented
5 months ago @gsamaras I suspect this was caused by the --mixed_precision bf16 and related configurations. The current implementation is natively on Ampere cards (or above) that support such tensor operations well.
gsamaras
commented
5 months ago If I try to execute with accelerate_launch, I get the same problem as in https://github.com/KimMeen/Time-LLM/issues/1#issuecomment-1925634459.
If I try to execute with python run_main.py I get the RuntimeError: expected scalar type Float but found BFloat16 error. The mixed precision parameter is only used in accelerate launch, when executing with python it's not recognized.
Do you have an online notebook I could use where you have a working instance of your model?
KimMeen
commented
5 months ago @gsamaras please use accelerate launch and make sure you have correctly configurated num_process as I mentioned in #1. You may also refer to https://github.com/paperswithcode/galai/issues/3 for the error of RuntimeError: CUDA error: invalid device ordinal. The default configuration and scripts should be ready to use on an instance with 8*A100.
gsamaras
commented
5 months ago I changed num_processes to the no of GPUs. Even if I try to run with fp16 (while changing it in deepseed config too), I get:
: mat1 and mat2 must have the same dtype, but got Float and HalfRuntimeError
: mat1 and mat2 must have the same dtype, but got Float and HalfAre you aware where I can find a free online instance with A100 for a basic demo of your code @KimMeen? Kaggle? Colab maybe?
KimMeen
commented
5 months ago @gsamaras The error you encountered may be caused by this: https://github.com/KimMeen/Time-LLM/blob/39d7d77c02d9c1c7c440d35faffeecb35fca7d8c/models/TimeLLM.py#L144
Slight modifications, like the one mentioned above, are needed if you are not using Ampere cards. You may refer to this for information on GPU instances.
aliper96
commented
5 months ago `for ii in range(args.itr):
setting = '{}_{}_{}_{}_ft{}_sl{}_ll{}_pl{}_dm{}_nh{}_el{}_dl{}_df{}_fc{}_eb{}_{}_{}'.format(
args.task_name,
args.model_id,
args.model,
args.data,
args.features,
args.seq_len,
args.label_len,
args.pred_len,
args.d_model,
args.n_heads,
args.e_layers,
args.d_layers,
args.d_ff,
args.factor,
args.embed,
args.des, ii)
train_data, train_loader = data_provider(args, 'train')
vali_data, vali_loader = data_provider(args, 'val')
test_data, test_loader = data_provider(args, 'test')
if args.model == 'Autoformer':
model = Autoformer.Model(args).float()
elif args.model == 'DLinear':
model = DLinear.Model(args).float()
else:
model = TimeLLM.Model(args).float()
model = model.to(torch.bfloat16)
path = os.path.join(args.checkpoints,
setting + '-' + args.model_comment) # unique checkpoint saving path
args.content = load_content(args)
if not os.path.exists(path) and accelerator.is_local_main_process:
os.makedirs(path)
time_now = time.time()
train_steps = len(train_loader)
early_stopping = EarlyStopping(accelerator=accelerator, patience=args.patience)
trained_parameters = []
for p in model.parameters():
if p.requires_grad is True:
trained_parameters.append(p)
model_optim = optim.Adam(trained_parameters, lr=args.learning_rate)
if args.lradj == 'COS':
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(model_optim, T_max=20, eta_min=1e-8)
else:
scheduler = lr_scheduler.OneCycleLR(optimizer=model_optim,
steps_per_epoch=train_steps,
pct_start=args.pct_start,
epochs=args.train_epochs,
max_lr=args.learning_rate)
criterion = nn.MSELoss()
mae_metric = nn.L1Loss()
train_loader, vali_loader, test_loader, model, model_optim, scheduler = accelerator.prepare(
train_loader, vali_loader, test_loader, model, model_optim, scheduler)
if args.use_amp:
scaler = torch.cuda.amp.GradScaler()
for epoch in range(args.train_epochs):
iter_count = 0
train_loss = []
model.train()
epoch_time = time.time()
for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in tqdm(enumerate(train_loader)):
iter_count += 1
model_optim.zero_grad()
batch_x = batch_x.float().to(accelerator.device)
batch_y = batch_y.float().to(accelerator.device)
batch_x_mark = batch_x_mark.float().to(accelerator.device)
batch_y_mark = batch_y_mark.float().to(accelerator.device)
# decoder input
dec_inp = torch.zeros_like(batch_y[:, -args.pred_len:, :]).float().to(
accelerator.device)
dec_inp = torch.cat([batch_y[:, :args.label_len, :], dec_inp], dim=1).float().to(
accelerator.device)
# encoder - decoder
if args.use_amp:
with torch.cuda.amp.autocast():
if args.output_attention:
outputs = model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
else:
outputs = model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
f_dim = -1 if args.features == 'MS' else 0
outputs = outputs[:, -args.pred_len:, f_dim:]
batch_y = batch_y[:, -args.pred_len:, f_dim:].to(accelerator.device)
loss = criterion(outputs, batch_y)
train_loss.append(loss.item())
else:
if args.output_attention:
outputs = model(batch_x, batch_x_mark, dec_inp, batch_y_mark)[0]
else:
outputs = model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
f_dim = -1 if args.features == 'MS' else 0
outputs = outputs[:, -args.pred_len:, f_dim:]
batch_y = batch_y[:, -args.pred_len:, f_dim:]
loss = criterion(outputs, batch_y)
train_loss.append(loss.item())
if (i + 1) % 100 == 0:
accelerator.print(
"\titers: {0}, epoch: {1} | loss: {2:.7f}".format(i + 1, epoch + 1, loss.item()))
speed = (time.time() - time_now) / iter_count
left_time = speed * ((args.train_epochs - epoch) * train_steps - i)
accelerator.print('\tspeed: {:.4f}s/iter; left time: {:.4f}s'.format(speed, left_time))
iter_count = 0
time_now = time.time()
if args.use_amp:
scaler.scale(loss).backward()
scaler.step(model_optim)
scaler.update()
else:
accelerator.backward(loss)
model_optim.step()
if args.lradj == 'TST':
adjust_learning_rate(accelerator, model_optim, scheduler, epoch + 1, args, printout=False)
scheduler.step()
accelerator.print("Epoch: {} cost time: {}".format(epoch + 1, time.time() - epoch_time))
train_loss = np.average(train_loss)
vali_loss, vali_mae_loss = vali(args, accelerator, model, vali_data, vali_loader, criterion, mae_metric)
test_loss, test_mae_loss = vali(args, accelerator, model, test_data, test_loader, criterion, mae_metric)
accelerator.print(
"Epoch: {0} | Train Loss: {1:.7f} Vali Loss: {2:.7f} Test Loss: {3:.7f} MAE Loss: {4:.7f}".format(
epoch + 1, train_loss, vali_loss, test_loss, test_mae_loss))
early_stopping(vali_loss, model, path)
if early_stopping.early_stop:
accelerator.print("Early stopping")
break
if args.lradj != 'TST':
if args.lradj == 'COS':
scheduler.step()
accelerator.print("lr = {:.10f}".format(model_optim.param_groups[0]['lr']))
else:
if epoch == 0:
args.learning_rate = model_optim.param_groups[0]['lr']
accelerator.print("lr = {:.10f}".format(model_optim.param_groups[0]['lr']))
adjust_learning_rate(accelerator, model_optim, scheduler, epoch + 1, args, printout=True)
else:
accelerator.print('Updating learning rate to {}'.format(scheduler.get_last_lr()[0]))accelerator.wait_for_everyone() ` this worked for me, also in windows
aliper96
commented
5 months ago ddp_kwargs = DistributedDataParallelKwargs(find_unused_parameters=True) accelerator = Accelerator(kwargs_handlers=[ddp_kwargs]) also had to remove the deepspeed dependency like this the only change in the previous code is tha i converted the entire model to 16 bits with this line : model = model.to(torch.bfloat16)
gsamaras
commented
5 months ago @aliper96 thanks for joining in, can you provide a minimal complete and reproducible example please?
aliper96
commented
5 months ago alitimellm.zip here you have the notebook
gsamaras
commented
5 months ago @aliper96 I think I'm close, but I get the following error, something with the paths maybe? Check it live in Kaggle here:
---------------------------------------------------------------------------
HFValidationError Traceback (most recent call last)
File /opt/conda/lib/python3.10/site-packages/transformers/utils/hub.py:385, in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)
383 try:
384 # Load from URL or cache if already cached
--> 385 resolved_file = hf_hub_download(
386 path_or_repo_id,
387 filename,
388 subfolder=None if len(subfolder) == 0 else subfolder,
389 repo_type=repo_type,
390 revision=revision,
391 cache_dir=cache_dir,
392 user_agent=user_agent,
393 force_download=force_download,
394 proxies=proxies,
395 resume_download=resume_download,
396 token=token,
397 local_files_only=local_files_only,
398 )
399 except GatedRepoError as e:
File /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:110, in validate_hf_hub_args.<locals>._inner_fn(*args, **kwargs)
109 if arg_name in ["repo_id", "from_id", "to_id"]:
--> 110 validate_repo_id(arg_value)
112 elif arg_name == "token" and arg_value is not None:
File /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:158, in validate_repo_id(repo_id)
157 if repo_id.count("/") > 1:
--> 158 raise HFValidationError(
159 "Repo id must be in the form 'repo_name' or 'namespace/repo_name':"
160 f" '{repo_id}'. Use `repo_type` argument if needed."
161 )
163 if not REPO_ID_REGEX.match(repo_id):
HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/'. Use `repo_type` argument if needed.
The above exception was the direct cause of the following exception:
OSError Traceback (most recent call last)
Cell In[22], line 30
28 model = DLinear.Model(args).float()
29 else:
---> 30 model = TimeLLM.Model(args).float()
32 model = model.to(torch.bfloat16)
35 path = os.path.join(args.checkpoints,
36 setting + '-' + args.model_comment) # unique checkpoint saving path
File /kaggle/working/Time-LLM/models/TimeLLM.py:44, in Model.__init__(self, configs, patch_len, stride)
41 self.patch_len = configs.patch_len
42 self.stride = configs.stride
---> 44 self.llama_config = LlamaConfig.from_pretrained('/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/')
45 # self.llama_config = LlamaConfig.from_pretrained('huggyllama/llama-7b')
46 self.llama_config.num_hidden_layers = configs.llm_layers
File /opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:605, in PretrainedConfig.from_pretrained(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, **kwargs)
601 kwargs["revision"] = revision
603 cls._set_token_in_kwargs(kwargs, token)
--> 605 config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
606 if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
607 logger.warning(
608 f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
609 f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
610 )
File /opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:634, in PretrainedConfig.get_config_dict(cls, pretrained_model_name_or_path, **kwargs)
632 original_kwargs = copy.deepcopy(kwargs)
633 # Get config dict associated with the base config file
--> 634 config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
635 if "_commit_hash" in config_dict:
636 original_kwargs["_commit_hash"] = config_dict["_commit_hash"]
File /opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:689, in PretrainedConfig._get_config_dict(cls, pretrained_model_name_or_path, **kwargs)
685 configuration_file = kwargs.pop("_configuration_file", CONFIG_NAME)
687 try:
688 # Load from local folder or from cache or download from model Hub and cache
--> 689 resolved_config_file = cached_file(
690 pretrained_model_name_or_path,
691 configuration_file,
692 cache_dir=cache_dir,
693 force_download=force_download,
694 proxies=proxies,
695 resume_download=resume_download,
696 local_files_only=local_files_only,
697 token=token,
698 user_agent=user_agent,
699 revision=revision,
700 subfolder=subfolder,
701 _commit_hash=commit_hash,
702 )
703 commit_hash = extract_commit_hash(resolved_config_file, commit_hash)
704 except EnvironmentError:
705 # Raise any environment error raise by `cached_file`. It will have a helpful error message adapted to
706 # the original exception.
File /opt/conda/lib/python3.10/site-packages/transformers/utils/hub.py:450, in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)
448 raise EnvironmentError(f"There was a specific connection error when trying to load {path_or_repo_id}:\n{err}")
449 except HFValidationError as e:
--> 450 raise EnvironmentError(
451 f"Incorrect path_or_model_id: '{path_or_repo_id}'. Please provide either the path to a local folder or the repo_id of a model on the Hub."
452 ) from e
453 return resolved_file
OSError: Incorrect path_or_model_id: '/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/'. Please provide either the path to a local folder or the repo_id of a model on the Hub.@aliper96 I think I'm close, but I get the following error, something with the paths maybe? Check it live in Kaggle here:
--------------------------------------------------------------------------- HFValidationError Traceback (most recent call last) File /opt/conda/lib/python3.10/site-packages/transformers/utils/hub.py:385, in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs) 383 try: 384 # Load from URL or cache if already cached --> 385 resolved_file = hf_hub_download( 386 path_or_repo_id, 387 filename, 388 subfolder=None if len(subfolder) == 0 else subfolder, 389 repo_type=repo_type, 390 revision=revision, 391 cache_dir=cache_dir, 392 user_agent=user_agent, 393 force_download=force_download, 394 proxies=proxies, 395 resume_download=resume_download, 396 token=token, 397 local_files_only=local_files_only, 398 ) 399 except GatedRepoError as e: File /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:110, in validate_hf_hub_args.<locals>._inner_fn(*args, **kwargs) 109 if arg_name in ["repo_id", "from_id", "to_id"]: --> 110 validate_repo_id(arg_value) 112 elif arg_name == "token" and arg_value is not None: File /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:158, in validate_repo_id(repo_id) 157 if repo_id.count("/") > 1: --> 158 raise HFValidationError( 159 "Repo id must be in the form 'repo_name' or 'namespace/repo_name':" 160 f" '{repo_id}'. Use `repo_type` argument if needed." 161 ) 163 if not REPO_ID_REGEX.match(repo_id): HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/'. Use `repo_type` argument if needed. The above exception was the direct cause of the following exception: OSError Traceback (most recent call last) Cell In[22], line 30 28 model = DLinear.Model(args).float() 29 else: ---> 30 model = TimeLLM.Model(args).float() 32 model = model.to(torch.bfloat16) 35 path = os.path.join(args.checkpoints, 36 setting + '-' + args.model_comment) # unique checkpoint saving path File /kaggle/working/Time-LLM/models/TimeLLM.py:44, in Model.__init__(self, configs, patch_len, stride) 41 self.patch_len = configs.patch_len 42 self.stride = configs.stride ---> 44 self.llama_config = LlamaConfig.from_pretrained('/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/') 45 # self.llama_config = LlamaConfig.from_pretrained('huggyllama/llama-7b') 46 self.llama_config.num_hidden_layers = configs.llm_layers File /opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:605, in PretrainedConfig.from_pretrained(cls, pretrained_model_name_or_path, cache_dir, force_download, local_files_only, token, revision, **kwargs) 601 kwargs["revision"] = revision 603 cls._set_token_in_kwargs(kwargs, token) --> 605 config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) 606 if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type: 607 logger.warning( 608 f"You are using a model of type {config_dict['model_type']} to instantiate a model of type " 609 f"{cls.model_type}. This is not supported for all configurations of models and can yield errors." 610 ) File /opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:634, in PretrainedConfig.get_config_dict(cls, pretrained_model_name_or_path, **kwargs) 632 original_kwargs = copy.deepcopy(kwargs) 633 # Get config dict associated with the base config file --> 634 config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) 635 if "_commit_hash" in config_dict: 636 original_kwargs["_commit_hash"] = config_dict["_commit_hash"] File /opt/conda/lib/python3.10/site-packages/transformers/configuration_utils.py:689, in PretrainedConfig._get_config_dict(cls, pretrained_model_name_or_path, **kwargs) 685 configuration_file = kwargs.pop("_configuration_file", CONFIG_NAME) 687 try: 688 # Load from local folder or from cache or download from model Hub and cache --> 689 resolved_config_file = cached_file( 690 pretrained_model_name_or_path, 691 configuration_file, 692 cache_dir=cache_dir, 693 force_download=force_download, 694 proxies=proxies, 695 resume_download=resume_download, 696 local_files_only=local_files_only, 697 token=token, 698 user_agent=user_agent, 699 revision=revision, 700 subfolder=subfolder, 701 _commit_hash=commit_hash, 702 ) 703 commit_hash = extract_commit_hash(resolved_config_file, commit_hash) 704 except EnvironmentError: 705 # Raise any environment error raise by `cached_file`. It will have a helpful error message adapted to 706 # the original exception. File /opt/conda/lib/python3.10/site-packages/transformers/utils/hub.py:450, in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs) 448 raise EnvironmentError(f"There was a specific connection error when trying to load {path_or_repo_id}:\n{err}") 449 except HFValidationError as e: --> 450 raise EnvironmentError( 451 f"Incorrect path_or_model_id: '{path_or_repo_id}'. Please provide either the path to a local folder or the repo_id of a model on the Hub." 452 ) from e 453 return resolved_file OSError: Incorrect path_or_model_id: '/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/'. Please provide either the path to a local folder or the repo_id of a model on the Hub.
@gsamaras Simply use 'huggyllama/llama-7b' instead of '/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/' in TimeLLM.py will solve this issue.
aliper96
commented
5 months ago @KimMeen I'm PhD student in generative AI and thanks for the code... most clean and understandle code!!
gsamaras
commented
5 months ago @KimMeen unfortunately when changing this, I this error:
ImportError: Using `load_in_8bit=True` requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes `pip install -i https://test.pypi.org/simple/ bitsandbytes` or `pip install bitsandbytes`.although I installed both packages.
KimMeen
commented
5 months ago @gsamaras Remove load_in_8bit=True and have a try
gsamaras
commented
5 months ago @KimMeen it seems I don't have control there, it's not in your code, see the full error please:
---------------------------------------------------------------------------
ImportError Traceback (most recent call last)
Cell In[32], line 30
28 model = DLinear.Model(args).float()
29 else:
---> 30 model = Model(args).float() #TimeLLM.Model(args).float()
32 model = model.to(torch.bfloat16)
35 path = os.path.join(args.checkpoints,
36 setting + '-' + args.model_comment) # unique checkpoint saving path
Cell In[12], line 55, in Model.__init__(self, configs, patch_len, stride)
53 self.llama_config.output_attentions = True
54 self.llama_config.output_hidden_states = True
---> 55 self.llama = LlamaModel.from_pretrained(
56 #"/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/",
57 'huggyllama/llama-7b',
58 trust_remote_code=True,
59 local_files_only=True,
60 config=self.llama_config,
61 load_in_4bit=True
62 )
64 self.tokenizer = LlamaTokenizer.from_pretrained(
65 #"/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/tokenizer.model",
66 'huggyllama/llama-7b',
67 trust_remote_code=True,
68 local_files_only=True
69 )
71 if self.tokenizer.eos_token:
File /opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py:3034, in PreTrainedModel.from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)
3032 raise RuntimeError("No GPU found. A GPU is needed for quantization.")
3033 if not (is_accelerate_available() and is_bitsandbytes_available()):
-> 3034 raise ImportError(
3035 "Using `load_in_8bit=True` requires Accelerate: `pip install accelerate` and the latest version of"
3036 " bitsandbytes `pip install -i https://test.pypi.org/simple/ bitsandbytes` or"
3037 " `pip install bitsandbytes`."
3038 )
3040 if torch_dtype is None:
3041 # We force the `dtype` to be float16, this is a requirement from `bitsandbytes`
3042 logger.info(
3043 f"Overriding torch_dtype={torch_dtype} with `torch_dtype=torch.float16` due to "
3044 "requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. "
3045 "Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass"
3046 " torch_dtype=torch.float16 to remove this warning."
3047 )
ImportError: Using `load_in_8bit=True` requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes `pip install -i https://test.pypi.org/simple/ bitsandbytes` or `pip install bitsandbytes`.@gsamaras Will removing load_in_4bit=True works on your end? See also https://huggingface.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g/discussions/11
gsamaras
commented
5 months ago No, sorry:
---------------------------------------------------------------------------
OSError Traceback (most recent call last)
Cell In[45], line 30
28 model = DLinear.Model(args).float()
29 else:
---> 30 model = Model(args).float() #TimeLLM.Model(args).float()
32 model = model.to(torch.bfloat16)
35 path = os.path.join(args.checkpoints,
36 setting + '-' + args.model_comment) # unique checkpoint saving path
Cell In[42], line 54, in Model.__init__(self, configs, patch_len, stride)
52 self.llama_config.output_attentions = True
53 self.llama_config.output_hidden_states = True
---> 54 self.llama = LlamaModel.from_pretrained(
55 #"/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/",
56 'huggyllama/llama-7b',
57 trust_remote_code=True,
58 local_files_only=True,
59 config=self.llama_config,
60 load_in_4bit=False
61 )
63 self.tokenizer = LlamaTokenizer.from_pretrained(
64 #"/mnt/alps/modelhub/pretrained_model/LLaMA/7B_hf/tokenizer.model",
65 'huggyllama/llama-7b',
66 trust_remote_code=True,
67 local_files_only=True
68 )
70 if self.tokenizer.eos_token:
File /opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py:3455, in from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)
3452 return key.replace("gamma", "weight")
3453 return key
-> 3455 original_loaded_keys = loaded_keys
3456 loaded_keys = [_fix_key(key) for key in loaded_keys]
3458 if len(prefix) > 0:
OSError: huggyllama/llama-7b does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack
I am trying to run the ETTm1 example, but despite a plethora of efforts, I keep getting: