9 contributors

History: 10 commits

YenChunChen

make flash attention usage configurable from user code

bfc0c05 4 months ago

.gitattributes

1.52 kB

initial commit 4 months ago
CODE_OF_CONDUCT.md

444 Bytes

chore(root): Initial files upload. 4 months ago
LICENSE

1.14 kB

chore(root): Initial files upload. 4 months ago
README.md

15.9 kB

Update README.md (#14) 4 months ago
SECURITY.md

2.66 kB

chore(root): Initial files upload. 4 months ago
SUPPORT.md

1.24 kB

chore(root): Initial files upload. 4 months ago
config.json
3.62 kB

make flash attention usage configurable from user code 4 months ago
configuration_phi3_v.py

10.6 kB

chore(root): Initial files upload. 4 months ago
image_embedding_phi3_v.py

14.1 kB

chore(root): Initial files upload. 4 months ago
image_processing_phi3_v.py

11.4 kB

correct the paper reference (#25) 4 months ago
model-00001-of-00002.safetensors
4.94 GB
LFS

chore(root): Initial files upload. 4 months ago
model-00002-of-00002.safetensors

3.35 GB
LFS

chore(root): Initial files upload. 4 months ago
model.safetensors.index.json

68.9 kB

chore(root): Initial files upload. 4 months ago
modeling_phi3_v.py

75.4 kB

make flash attention usage configurable from user code 4 months ago
preprocessor_config.json

464 Bytes

chore(root): Initial files upload. 4 months ago
processing_phi3_v.py

11.3 kB

chore(root): Initial files upload. 4 months ago
sample_inference.py

6.86 kB

chore(root): Initial files upload. 4 months ago
special_tokens_map.json

670 Bytes

chore(root): Initial files upload. 4 months ago
tokenizer.json

1.85 MB

chore(root): Initial files upload. 4 months ago
tokenizer_config.json

9.4 kB

chore(root): Initial files upload. 4 months ago