Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
microsoft
/
Phi-3.5-vision-instruct
like
518
Image-Text-to-Text
Transformers
Safetensors
multilingual
phi3_v
text-generation
nlp
code
vision
conversational
custom_code
arxiv:
2404.14219
License:
mit
Model card
Files
Files and versions
Community
31
Train
Deploy
Use this model
main
Phi-3.5-vision-instruct
9 contributors
History:
12 commits
haipingwu
fix_rope_scaling (
#28
)
4a0d683
verified
16 days ago
.gitattributes
1.52 kB
initial commit
about 2 months ago
CODE_OF_CONDUCT.md
444 Bytes
upload initial files
about 2 months ago
LICENSE
1.14 kB
upload initial files
about 2 months ago
README.md
18.8 kB
Add proper library name (#23)
about 1 month ago
SECURITY.md
2.66 kB
upload initial files
about 2 months ago
SUPPORT.md
1.24 kB
upload initial files
about 2 months ago
config.json
3.78 kB
upload initial files
about 2 months ago
configuration_phi3_v.py
10.7 kB
upload model card
about 2 months ago
generation_config.json
136 Bytes
upload initial files
about 2 months ago
model-00001-of-00002.safetensors
4.94 GB
LFS
upload initial files
about 2 months ago
model-00002-of-00002.safetensors
3.35 GB
LFS
upload initial files
about 2 months ago
model.safetensors.index.json
68.9 kB
upload initial files
about 2 months ago
modeling_phi3_v.py
88.9 kB
fix_rope_scaling (#28)
16 days ago
preprocessor_config.json
442 Bytes
Fix AutoImageProcessor mapping (#4)
about 2 months ago
processing_phi3_v.py
22 kB
fix_import (#1)
about 2 months ago
processor_config.json
119 Bytes
upload initial files
about 2 months ago
sample_inference.py
6.78 kB
upload initial files
about 2 months ago
special_tokens_map.json
670 Bytes
upload initial files
about 2 months ago
tokenizer.json
1.85 MB
upload initial files
about 2 months ago
tokenizer_config.json
9.52 kB
upload initial files
about 2 months ago