5 contributors

History: 40 commits

hemanham

remove imports and use of flash attention

0d80022 20 days ago

assets
Create README.md about 2 months ago
.gitattributes

1.64 kB

Create README.md about 2 months ago
README.md

15.5 kB

Update README.md about 1 month ago
added_tokens.json

629 Bytes

init about 2 months ago
config.json

1.37 kB

init about 2 months ago
configuration_minicpm.py

3.28 kB

Add vision_batch_size to avoid cuda OOM (#4) about 2 months ago
generation_config.json

121 Bytes

init about 2 months ago
image_processing_minicpmv.py

16.6 kB

add kwargs for processor about 2 months ago
merges.txt

1.67 MB

init about 2 months ago
model-00001-of-00004.safetensors
4.87 GB
LFS

Add model file about 2 months ago
model-00002-of-00004.safetensors
4.93 GB
LFS

Add model file about 2 months ago
model-00003-of-00004.safetensors
4.33 GB
LFS

Add model file about 2 months ago
model-00004-of-00004.safetensors

2.06 GB
LFS

Add model file about 2 months ago
model.safetensors.index.json

66.8 kB

init about 2 months ago
modeling_minicpmv.py
15.5 kB

remove imports and use of flash attention 20 days ago
modeling_navit_siglip.py
32.4 kB

remove imports and use of flash attention 20 days ago
preprocessor_config.json

714 Bytes

init about 2 months ago
processing_minicpmv.py

10 kB

add kwargs for processor about 2 months ago
resampler.py

34.7 kB

init about 2 months ago
special_tokens_map.json

3.56 kB

init about 2 months ago
tokenization_minicpmv_fast.py

1.66 kB

init about 2 months ago
tokenizer.json

7.03 MB

init about 2 months ago
tokenizer_config.json

5.64 kB

init about 2 months ago
vocab.json

2.78 MB

init about 2 months ago