2 contributors

History: 4 commits

Daniël de Kok

Use Torch attention implementation

a0351e0 over 1 year ago

.gitattributes

1.52 kB

initial commit over 1 year ago
adapt_tokenizer.py

1.75 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
attention.py

17.7 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
blocks.py

2.55 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
config.json

771 Bytes

Use Torch attention implementation over 1 year ago
configuration_mpt.py

9.2 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
custom_embedding.py

305 Bytes

Try to make MPT tests work without MPT in a transformers release over 1 year ago
flash_attn_triton.py

28.2 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
generation_config.json

96 Bytes

Add MPT test over 1 year ago
hf_prefixlm_converter.py

27.2 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
meta_init_context.py

3.64 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
modeling_mpt.py

19.3 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
norm.py

2.56 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
param_init_fns.py

12.6 kB

Try to make MPT tests work without MPT in a transformers release over 1 year ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
388 kB
LFS

Add MPT test over 1 year ago

Detected Pickle imports (3)