1 contributor

History: 9 commits

emozilla

add kv cache

bbaa409 almost 2 years ago

.gitattributes

1.48 kB

initial commit almost 2 years ago
README.md

4.72 kB

Update README.md almost 2 years ago
adapt_tokenizer.py

1.76 kB

initial commit almost 2 years ago
attention.py

25.5 kB

add kv cache almost 2 years ago
blocks.py

2.71 kB

add kv cache almost 2 years ago
config.json

1.25 kB

add kv cache almost 2 years ago
configuration_mpt.py

9.29 kB

initial commit almost 2 years ago
flash_attn_triton.py

28.9 kB

initial commit almost 2 years ago
generation_config.json

111 Bytes

add kv cache almost 2 years ago
hf_prefixlm_converter.py

27.6 kB

initial commit almost 2 years ago
is_torch_version.py

2.39 kB

add Birchlabs MPT changes almost 2 years ago
meta_init_context.py

3.68 kB

initial commit almost 2 years ago
modeling_mpt.py

21.2 kB

add kv cache almost 2 years ago
norm.py

2.59 kB

initial commit almost 2 years ago
param_init_fns.py

12.7 kB

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

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

initial commit almost 2 years ago
pytorch_model.bin.index.json

16 kB

initial commit almost 2 years ago
special_tokens_map.json

131 Bytes

initial commit almost 2 years ago
tokenizer.json

2.11 MB

initial commit almost 2 years ago
tokenizer_config.json

237 Bytes

initial commit almost 2 years ago

Detected Pickle imports (3)

Detected Pickle imports (3)