9 contributors

History: 12 commits

rogerxfeng8

Moved flash_attn assert close to the caller

e477000 verified 4 months ago

.gitattributes

1.52 kB

chore(root): Initial files upload. 8 months ago
CODE_OF_CONDUCT.md

444 Bytes

Initial commit 8 months ago
LICENSE

1.08 kB

chore(root): Initial files upload. 8 months ago
NOTICE.md

1.77 kB

chore(root): Initial files upload. 8 months ago
README.md

19.4 kB

Update README.md 4 months ago
SECURITY.md

2.66 kB

Initial commit 8 months ago
cl100k_base.tiktoken

1.68 MB

chore(root): Initial files upload. 8 months ago
config.json

4.02 kB

Add attention_bias to make TGI work (#4) 7 months ago
configuration_phi3_small.py

12.3 kB

chore(root): Initial files upload. 8 months ago
generation_config.json

142 Bytes

chore(root): Initial files upload. 8 months ago
model-00001-of-00004.safetensors

4.83 GB
LFS

chore(root): Initial files upload. 8 months ago
model-00002-of-00004.safetensors

4.8 GB
LFS

chore(root): Initial files upload. 8 months ago
model-00003-of-00004.safetensors

4.8 GB
LFS

chore(root): Initial files upload. 8 months ago
model-00004-of-00004.safetensors

352 MB
LFS

chore(root): Initial files upload. 8 months ago
model.safetensors.index.json

32.1 kB

chore(root): Initial files upload. 8 months ago
modeling_phi3_small.py

48 kB

Moved flash_attn assert close to the caller 4 months ago
positional_embedding.py

11.7 kB

chore(root): Initial files upload. 8 months ago
special_tokens_map.json

99 Bytes

chore(root): Initial files upload. 8 months ago
tokenization_phi3_small.py

11.5 kB

Update tokenization_phi3_small.py (#14) 7 months ago
tokenizer_config.json

638 Bytes

chore(root): Initial files upload. 8 months ago
triton_blocksparse_attention_layer.py

7.2 kB

chore(root): Initial files upload. 8 months ago
triton_flash_blocksparse_attn.py

82.5 kB

chore(root): Initial files upload. 8 months ago