Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
Hi, I have been trying to use texar-pytorch in my experiments, but when I try to use the GPT2Decoder module, I get HTTP 404 error. I am getting this error for both gpt2-small and gpt2-medium. Is the model missing? This is the traceback of the error:
Traceback (most recent call last):
File "texar_enc_dec.py", line 113, in
main(args)
File "texar_enc_dec.py", line 79, in main
model = ConditionalGPT2Model(args, datasets["train"].target_vocab.size)
File "texar_enc_dec.py", line 18, in __init__
self.decoder = tx.modules.GPT2Decoder("gpt2-small")
File "/home/t-rsarkar/.local/lib/python3.7/site-packages/texar/torch/modules/decoders/gpt2_decoder.py", line 69, in __init__
self.load_pretrained_config(pretrained_model_name, cache_dir)
File "/home/t-rsarkar/.local/lib/python3.7/site-packages/texar/torch/modules/pretrained/pretrained_base.py", line 138, in load_pretrained_config
self.pretrained_model_name, cache_dir)
File "/home/t-rsarkar/.local/lib/python3.7/site-packages/texar/torch/modules/pretrained/pretrained_base.py", line 220, in download_checkpoint
maybe_download(path, cache_path)
File "/home/t-rsarkar/.local/lib/python3.7/site-packages/texar/torch/data/data_utils.py", line 105, in maybe_download
filepath = _download(url, filename, path)
File "/home/t-rsarkar/.local/lib/python3.7/site-packages/texar/torch/data/data_utils.py", line 132, in _download
filepath, _ = urllib.request.urlretrieve(url, filepath, _progress_hook)
File "/anaconda/envs/py37_default/lib/python3.7/urllib/request.py", line 247, in urlretrieve
with contextlib.closing(urlopen(url, data)) as fp:
File "/anaconda/envs/py37_default/lib/python3.7/urllib/request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "/anaconda/envs/py37_default/lib/python3.7/urllib/request.py", line 531, in open
response = meth(req, response)
File "/anaconda/envs/py37_default/lib/python3.7/urllib/request.py", line 641, in http_response
'http', request, response, code, msg, hdrs)
File "/anaconda/envs/py37_default/lib/python3.7/urllib/request.py", line 569, in error
return self._call_chain(*args)
File "/anaconda/envs/py37_default/lib/python3.7/urllib/request.py", line 503, in _call_chain
result = func(*args)
File "/anaconda/envs/py37_default/lib/python3.7/urllib/request.py", line 649, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found
I am using the following versions of the libraries:
texar-pytorch==0.1.2.post1
torch==1.8.1
Any help will be appreciated. I may be doing some stupid mistake, so, forgive me in advance.
Hi, I have been trying to use
texar-pytorch
in my experiments, but when I try to use theGPT2Decoder
module, I get HTTP 404 error. I am getting this error for bothgpt2-small
andgpt2-medium
. Is the model missing? This is the traceback of the error:I am using the following versions of the libraries:
Any help will be appreciated. I may be doing some stupid mistake, so, forgive me in advance.