1 contributor

History: 15 commits

muelletm

Make sure hidden state and wte weights are on same device when in parallel model.

28721e3 over 1 year ago

.gitattributes

1.48 kB

initial commit almost 2 years ago
README.md

11.6 kB

Upload 16 files almost 2 years ago
adapt_tokenizer.py

1.75 kB

Upload 16 files almost 2 years ago
attention.py

16.1 kB

Upload 16 files almost 2 years ago
blocks.py

2.49 kB

Upload 16 files almost 2 years ago
config.json

1.23 kB

Rename config (1).json to config.json almost 2 years ago
configuration_mpt.py

9.08 kB

Upload 16 files almost 2 years ago
generation_config.json

91 Bytes

Upload 16 files almost 2 years ago
hf_prefixlm_converter.py

27.2 kB

Upload 16 files almost 2 years ago
meta_init_context.py

3.64 kB

Upload 16 files almost 2 years ago
modeling_mpt.py

19.8 kB

Make sure hidden state and wte weights are on same device when in parallel model. over 1 year ago
norm.py

2.56 kB

Upload 16 files almost 2 years ago
param_init_fns.py

12.6 kB

Upload 16 files almost 2 years ago
pytorch_model-00001-of-00002.bin
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
9.94 GB
LFS

Upload pytorch_model-00001-of-00002.bin almost 2 years ago
pytorch_model-00002-of-00002.bin
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
3.36 GB
LFS

Upload pytorch_model-00002-of-00002.bin almost 2 years ago
pytorch_model.bin.index.json

16 kB

Rename pytorch_model.bin.index (2).json to pytorch_model.bin.index.json almost 2 years ago
special_tokens_map.json

99 Bytes

Upload 16 files almost 2 years ago
tokenizer.json

2.11 MB

Rename tokenizer (1).json to tokenizer.json almost 2 years ago
tokenizer_config.json

237 Bytes

Rename tokenizer_config (2).json to tokenizer_config.json almost 2 years ago

Detected Pickle imports (3)

Detected Pickle imports (3)